ABBYY FineReader Engine for Windows is a comprehensive software development kit (SDK) for document recognition and PDF conversion. It includes all the core technologies needed for developing powerful and intelligent document recognition, document conversion and data capture systems:

• optical character recognition (OCR),
• intelligent character recognition (ICR),
• optical mark recognition (OMR),
• optical barcode recognition (OBR),
• document imaging,
• PDF, PDF/A conversion

The FineReader Engine OCR SDK offers powerful image processing tools, document layout analysis and advanced PDF conversion and compression with support for various types of PDF, including PDF/A and compressed Mixed Raster Content (MRC) standard.

The ABBYY's OCR engine also delivers field-level/zonal recognition capabilities to support key business processes such as key-word classification, keyword indexing, and forms processing.

The version 9.0 of ABBYY FineReader Engine for Windows delivers high-quality recognition technologies with revolutionary enhancements:

• Adaptive Document Recognition technology (ADRT) allows re-creation of document logical structure and formatting attributes including headers, footers, page numbers, fonts and styles, and more.
• Multi-core Recognition Architecture facilitates processing speed on multi-core processors during image analysis and document recognition.
• Significant accuracy increase for Chinese, Japanese and Korean OCR

ABBYY's innovative OCR technologies have been awarded by government agencies and industry leading publications worldwide, recognizing the quality and success of the entire FineReader product line.

The OCR engine provides processing features designed specifically for large-scale and international projects:

• Balanced Mode Recognition,
• Document Analysis for Invoices,
• Document Analysis for Full-Text Indexing,
• The broadest language support with almost 200 languages for OCR and more than 110 languages for ICR.

The ABBYY FineReader Engine's API delivers a variety of powerful document processing functions and technologies, including:

ABBYY FineReader Engine 8.0 for Mac is a powerful, flexible tool to integrate optical character recognition (OCR), barcode recognition and PDF conversion functions into applications running on the Mac OS® X platform. With the SDK, software developers working wuth Mac can take advantage of the top-ranked ABBYY OCR technology that has been licensed by many world's leading software and hardware providers including Canon, DICOM/Kofax, EMC/Captiva, Microsoft, Microtek, NewSoft, Notable Solutions, Samsung Electronics and more (see the case studies).

The ABBYY FineReader Engine 8.0 for Mac delivers a wide range of document recognition functions to integrate into a variety of applications including word processors, scanning, archiving, search, document and information management, various applications for physically challenged users, and more. This version of the ABBYY SDK provides native support for both Intel® and PowerPC-based Mac computers and allows creating universal binary applications.

Image Manipulation and Pre-processing

The ABBYY FineReader Engine can receive images by two ways: getting directly from memory or opening from files. It supports major imaging formats, including multi-page TIFFs, JPEG 2000 (part 1), and works with black-and-white, grayscale and color images. It also opens PDF files.

The FineReader Engine also may save original and modified images into various formats. For the full list of input/output image formats, see the Specifications section.

Upon receiving images, the FineReader Engine can perform the following preprocessing functions to improve the recognition:

*Automatically de-skew images.

This feature is essential to be used especially when images come from scanners and requires a compensation for image skew. It does not require leading edge borders or lines.

*Split dual pages.

Works for scanning books as broadsides - both the left and right pages. The recognition quality is higher if, after scanning, the page is split into two, with each page corresponding to a single book page. Recognition and layout analysis are then performed separately for each page, along with de-skewing if required.

*Despeckle image (or image clean-up).

Designed to eliminate random noise (speckles). The image may have a large amount of "dust" present on it, i.e. a large number of excess dots. The dots arise in the case of documents of medium-to-low print quality, and dots located close to character outlines may have an adverse effect on recognition quality. These cases despeckle technique helps to improve the recognition quality.

*Texture Filtering and Adaptive binarization.

"noise" such as color and texture, increasing accuracy for difficult-to-read documents such as newsprint, color documents, faxes, and copies.



Innovative Adaptive Binarization technology dynamically adjusts threshold of brightness for each image fragment during the recognition. And by this usage of individual recognition parameters it produces significantly accurate recognition results for documents with gray or color variable contrast background and textures.

*Auto-detection of page orientation (90, 180, 270 degrees).

This feature is very important if it is unknown which direction the image is scanned in. The FineReader system automatically detects the orientation of each page and corrects it, if needed.

*Adaptive image pre-processing for camera images. The new technology applies different processing algorithms and correct specific image distortion typically seen in digital camera images. This provides an average improvement of 40% better accuracy in digital camera OCR.

*Despeckling of an image in individual blocks (or zones), with the ability to specify the size of black dots.

The FineReader Engine also offers a number of useful pre-processing functions, allowing to manipulate images such as "image scaling", "image clipping", "creating previews", "rotating (90, 180, 270 degrees)", "mirroring" and "inverting".

Document Analysis and Full Layout Retention

The document analysis function set of FineReader Engine API solves such tasks as automatic document conversion with full-page layout retention, zoning OCR with manually located blocks, etc. It includes:

    * auto-detection of page orientation - 90, 180, 270 degrees;
    * auto-detection of text blocks, tables, barcodes and pictures;
    * auto-detection of vertical text in table cells;
    * manual block zoning (adding, removing and editing blocks);

The unique FineReader Engine features are:

    * Document Analysis for Archiving Tasks
      This function automatically detects and recognizes all text on documents including text embedded in pictures, charts, and diagrams. Developers may choose to use this mode of document analysis to extract exhaustive full-text information on documents needed for document index building (as in DMS, CMS, Archiving systems).
    * Document Analysis for Invoices
      A special document analysis function designed as a preprocessing engine for converting semi-structured documents, such as invoices, payment drafts, checks, transfers, business cards, agreement, health claim forms, resumes, etc. In this preprocessing role, this function has been designed to find as much text on these documents as possible, including characters and numbers - even if this information is located within stamps, pictures, logos or small-text areas. Unlike in standard full-page document analysis, this specialized document analysis assumes all printed information on the documents is text. It also ensures that important text information is not identified as graphic elements and that words or numerical values are not separated into multiple characters. As a result, maximum information about the text, including its coordinates, is available for analysis, field-by-field processing and parsing at subsequent processing stages by other systems.
    * Export to Multiple Formats including PDF, RTF,  RTF/DOC/WordML XML, and HTML with exact layout retention.

Recognition

OCR

    * Recognize 175 languages for OCR.
    * 170 languages with Latin, Cyrillic, Greek, Armenian and Hebrew characters.
    * 43 languages have dictionary/morphology support.
    * Recognition of multilingual documents.
    * Recognition of dot-matrix document.
    * Recognition of typewritten documents.
    * Fast mode recognition.
      Designed for high-volume document processing applications where speed is more important than accuracy. This mode increases processing speed by 200-250%, making it particularly useful with document management and archiving systems.
    * Recognition of OCR-A and OCR-B.
    * FineReader XIX.
      There are many old documents, books, and newspapers published in the 17-20th century all over the world. The set of functions called "FineReader XIX" provides a unique capability to recognize texts published in the period from 1600 till 1937 in English, French, German, Italian, and Spanish. FineReader XIX supports special fonts such as Fraktur, Schwabacher and the majority of Gothic fonts.

For the entire list of supported OCR languages, see the Specifications section.
Barcode Recognition

    * Recognition of 1D barcodes.
      For the full list of supported 1D barcodes, see the Specifications.
    * 2D barcode recognition (PDF417).
      The 2D Barcode recognition recognizes PDF417, the industry standard for 2D barcodes. PDF417 encodes up to 1.1 kilobytes of data, including text and graphics information.
    * Fast barcode extraction.
      This feature enables automatic finding and recognizing barcodes at any angle on a document. It works both for 1D and 2D barcodes.

Field-level/Zonal Recognition Support

The SDK provides powerful field-level/zonal recognition capabilities ensuring accuracy and speed enhancement on small fields/zones. This functionality is crucial for processing tasks like data extraction, key-word indexing, and keyword classification. Key functionality for field level or zonal recognition includes multilingual OCR and barcode recognition, including:

    * Definition of field content by setting alphabets and dictionaries.

    * Detection of in-filed spacing - Detection and recognition of fields where the spaces are allowed. The FineReader Engine 8.0 also allows use of dictionaries which contain word-combinations with spaces.

    * Text block despeckle, with the ability to specify the size of white or black «garbage».

    * External recognition tuning features - Provides integrators with multiple word-level and character-level hypothesis and allowing integrators to influence the hypothesis choice by inserting additional ranking criteria during the recognition process.

Back to Top

PDF Conversion

The SDK includes powerful PDF conversion technology with extensive functions for PDF input and output including:

    * PDF Security and Encryption Support:
          o The SDK supports a variety of PDF security settings, increasing its applicability for government agencies and other organizations demanding high security.
          o "Open File" password settings designed to prevent unauthorized access to a document.
          o Restriction of certain operations, such as printing, editing or extracting file content, by assigning permission passwords.
          o Support for the latest encryption standards.

    * Output in tagged PDF format - that can be "reflowed" to fit different page or screen widths. Ideal for use with handheld devices (PDAs) or screen readers typically used by visually impaired users.
    * Page size - Ability to set the size for all pages of a output PDF file.
    * Links in PDF files - Re-creates hyperlinks within a PDF file.

Development Platform Functionality and Throughput Management

The FineReader Engine 8 for Mac provides several features allowing integrators to achieve optimal recognition accuracy and processing speed for their applications. It supports balance processing mode and provides «ready-to-load» samples to reduce time for choosing proper parameters for common usage scenarios (e.g. conversion to searchable PDF, field-level recognition, archiving, and indexing).

    * Easy-to-use development tools.
      In addition to API, the FineReader Engine 8.0 provides a popular Command Line Interface (CLI) and «ready-to-use» samples for rapid implementation.
    * External recognition tuning features:
                + Providing integrators with multiple word-level and character-level hypothesis,
                + The ability to influence the hypothesis choice by inserting additional ranking criteria during the recognition process;
    * Throughput management - The FineReader Engine 8.0 provides several features allowing integrators to achieve optimal recognition accuracy and processing speed for their applications. The speed-accuracy balance can be adjusted due to 3 content processing modes - thorough, balanced and fast.
    * CLI-based 24/7 service, a background OCR process useful for customers who works in multitasking mode (e.g. ASPs and in-house services).

Receiving and Exporting Recognized Text

The FineReader Engine API provides a wide range of options for export of recognition results, including different levels of document reconstruction:

    * A set of different levels of text format retention during export to external formats (from simple text with no formatting to complete page layout retention, including columns, tables, frames, fonts, font size, paragraph styles, borders, etc.).
    * Providing access to detailed information about each recognized character.
    * A set of functions to post-editing and post-formatting of the recognized text before its exporting.
    * Exporting recognized text into various formats (full list of formats see in Specifications).
    * Retaining full page layout of documents.
    * Replacing uncertain characters with their corresponding images when saving in PDF format.
    * Retaining picture and text color in full.

Superior Accuracy and Multilingual OCR - With the award-winning ABBYY recognition technologies, the FineReader Engine provides unmatched accuracy widely appreciated by many customers and industry professionals. It accurately recognizes printed documents in 175 languages including languages with Latin, Cyrillic, Greek, Armenian and Hebrew characters. The SDK delivers the same accuracy for documents with mixed languages including those containing mixed right-to-left and left-to-right texts (e.g. English and Hebrew).

Comprehensive Technology Platform - The SDK provides a comprehensive platform with a wide range of full-page and field-level/zonal recognition functions optimized for different document processing tasks including: conversion of documents to editable and searchable formats, creation of PDF archives, processing of digital camera images, recognition of barcodes, recognition of invoices, and keyword and full-text indexing.

Easy Integration - ABBYY FineReader Engine 8.0 for Mac consists of a set of libraries that makes the core OCR functionality easily accessible for developers via an API or the Command Line Interface. For rapid and easy integration, the SDK provides a set of programming samples, header files for both C and C++ interfaces which allow developers and integrators to save time and effort significantly.

Flexible Architecture and Lisensing Scheme - The Engine's modular approach to architecture and licensing allows developers to choose the only functions they need while providing them with the ability to add additional functionality quickly.

OCR Languages

ABBYY FineReader Engine 8.0 for Mac recognizes 175 OCR languages including:

* 38 main languages which FineReader Engine provides dictionary support for:

Armenian (Eastern, Western, Grabar), Bulgarian, Catalan, Croatian, Czech, Danish, Dutch (Netherlands and Belgium), English, Estonian, Finnish, French, German (new and old spelling), Greek, Hebrew, Hungarian, Italian, Latvian, Lithuanian, Norwegian (Nynorsk and Bokmal), Polish, Portuguese (Portugal and Brazil), Romanian, Russian, Slovak, Spanish, Swedish, Tatar, Turkish and Ukrainian.

* 132 additional languages with Latin, Cyrillic or Greek characters:

Abkhaz, Adyghian, Afrikaans, Agul, Albanian, Altai, Avar, Aymara, Azerbaijani (Cyrillic), Azerbaijani (Latin), Basque, Belarusian, Bemba, Blackfoot, Breton, Bugotu, Buryat, Cebuano, Chamorro, Chechen, Chukchee, Chuvash, Corsican, Crimean Tatar, Crow, Dakota, Dargwa, Dungan, Eskimo (Cyrillic), Eskimo (Latin), Even, Evenki, Faeroese, Fijian, Frisian, Friulian, Gagauz, Galician, Ganda, German (Luxemburg), Guarani, Hani, Hausa, Hawaiian, Icelandic, Ingush, Irish, Jingpo, Kabardian, Kalmyk, Karachay-balkar, Karakalpak, Kasub, Kawa, Kazakh, Khakass, Khanty, Kikuyu, Kirghiz, Kongo, Koryak, Kpelle, Kumyk, Kurdish, Lak, Latin, Lezgi, Luba, Macedonian, Malagasy, Malay, Malinke, Maltese, Mansi, Maori, Mari, Maya, Miao, Minangkabau, Mohawk, Moldavian, Mongol, Mordvin, Nahuatl, Nenets, Nivkh, Nogay, Nyanja, Ojibway, Ossetian, Papiamento, Provencal, Quechua, Rhaeto-Romanic, Romany, Rundi, Russian (old spelling), Rwanda, Sami (Lappish), Samoan, Scottish Gaelic, Selkup, Serbian (Cyrillic), Serbian (Latin), Shona, Somali, Sorbian, Sotho, Sunda, Swahili, Swazi, Tabasaran, Tagalog, Tahitian, Tajik, Tok Pisin, Tongan, Tswana, Tun, Turkmen, Tuvinian, Udmurt, Uigur (Cyrillic), Uigur (Latin), Uzbek (Cyrillic), Uzbek (Latin), Welsh, Wolof, Xhosa, Yakut, Zapotec, Zulu.

FineReader XIX module for recognition of Fraktur or "black letter" texts written in 5 old European languages including English, French, German, Italian and Spanish (with dictionary support).

* Tools for creating user-defined languages


Barcode Types

* 1D: Check Code 39, Check Interleaved 25, Code 128, Code 39, EAN 13, EAN 8, Interleaved 25, CODABAR (without checksum), UCC Code 128, Code 2 of 5 (Industrial, IATA, Matrix), Code 93, UPC-A, UPC-E and Postnet.

* 2D: PDF 417.

Supported Image Formats

Format	Extension	Open	Save
BMP: uncompressed black and white, uncompressed gray, uncompressed color	bmp	+	+
DCX: 2-bit - black and white 4- and 8-bit - gray TrueColor	dcx	+	+
PCX: 2-bit - black and white 4- and 8-bit - gray	pcx	+	+
PCX: TrueColor		+
PNG: black and white, gray, color	png	+	+
JPEG 2000: gray, color	jp2, j2c	+	+
JPEG: gray, color	jpg, jpeg, jfif	+	+
PDF (Version 1.6 or earlier)	pdf	+	+
TIFF: black and white - uncompressed, CCITT3, CCITT4, Packbits, ZIP gray - uncompressed, Packbits, JPEG, ZIP TrueColor - uncompressed, JPEG, ZIP multi image TIFF	tif, tiff	+	+
TIFF: black and white - CCITT3FAX, LZW gray - LZW palette - uncompressed, Packbits, ZIP TrueColor - LZW	tif, tiff	+
GIF: black and white - LZW-compressed gray - LZW-compressed TrueColor - LZW-compressed	gif	+

Export Formats

RTF/DOC/WordXML, XML, XLS, HTML, PDF, PDF Image Only, DBF and TXT/CSV.

Message Languages

Dialogue captions, text, error and other program messages are available in English, German, French, Spanish, Italian, Dutch, Portuguese, Russian, and Swedish.

System Requirements

Operating System: Mac OS X (10.3.9+, 10.4.x, 10.5.x) Processor: PowerPC or Intel Macintosh 300 MHz or higher Memory: 128 MB RAM for Runtime License installation and 512 MB RAM for Developer License installation. Hard disk space: 500 MB for full installation and 70 MB for program operation.

ABBYY FineReader Engine 8.0 with Extended Platform Support is a powerful software development kit (SDK) for integrating optical character recognition (OCR), barcode recognition and PDF conversion technologies into applications running on the Linux® and FreeBSD® platforms. ABBYY FineReader Engine provides an efficient and flexible way to integrate document recognition and PDF conversion functions into a wide variety of applications including archiving and storage, document conversion and management, and content management.

The SDK also includes advanced document analysis capabilities specifically optimized for different recognition tasks, such as invoice processing and full-text indexing, and delivers field level/zonal recognition capabilities to support processes such as keyword classification and keyword indexing.

With the release of the ABBYY FineReader Engine 8.0 EPS, Linux and BSD application developers are able to use the powerful document recognition and conversion technologies already chosen by many leading vendors worldwide, including Canon, DICOM/Kofax, EMC/Captiva, Microsoft, Microtek, NewSoft, Notable Solutions, Samsung Electronics and others (see the case studies).

Image Manipulation and Pre-processing

ABBYY FineReader Engine can receive images by two ways: getting directly from memory or opening from files. It supports major imaging formats, including multi-page TIFFs, JPEG 2000 (part 1), and works with black-and-white, grayscale and color images. It also can open PDF files, converting them into images using Adobe® PDF Library Technology.
The FineReader Engine may also save original and modified images into various formats. For the full list of supported image formats, see the Specifications section.

Upon receiving images, the FineReader Engine can perform the following preprocessing functions to improve the recognition:

• Automatically de-skew images
  This feature is essential to be used especially when images come from scanners and requires a compensation for image skew. It does not require leading edge borders or lines.
• Split dual pages
  Works for scanning books as broadsides - both the left and right pages. The recognition quality is higher if, after scanning, the page is split into two, with each page corresponding to a single book page. Recognition and layout analysis are then performed separately for each page, along with de-skewing if required.
• Despeckle image (or image clean-up)
  Designed to eliminate random noise (speckles). The image may have a large amount of "dust" present on it, i.e. a large number of excess dots. The dots arise in the case of documents of medium-to-low print quality, and dots located close to character outlines may have an adverse effect on recognition quality. These cases despeckle technique helps to improve the recognition quality.
• Texture Filtering and Adaptive binarization
  Texture filtering technology helps to filter out background "noise" such as color and texture, increasing accuracy for difficult-to-read documents such as newsprint, color documents, faxes, and copies.

Innovative Adaptive Binarization technology dynamically adjusts threshold of brightness for each image fragment during the recognition. And by this usage of individual recognition parameters it produces significantly accurate recognition results for documents with gray or color variable contrast background and textures.

• Auto-detection of page orientation (90, 180, 270 degrees).
  This feature is very important when in a bulk imputing system it is unknown on which direction the image is scanned. The FineReader system automatically detects the orientation of each page and corrects it, if needed.
• Manipulating with text color and background manipulation inside rectangles.
  It is an important feature for customers working with document management systems (DMS). The typical scenario of using this feature in archiving business is the following. A recognized image is stored as image and as plain text in an archive. Archive index of text also contains the coordinates if each character on the image. When a user receives a result of searching through archive, he gets an image of document as a source. But on that image, using the mentioned FineReader Engine function, the searching text is highlighted, changing the text color and background color within a rectangle, which completely outlines a found text.
• Adaptive image pre-processing for camera images. The new technology applies different processing algorithms and correct specific image distortion typically seen in digital camera images. This provides an average improvement of 40% better accuracy in digital camera OCR.
• Despeckling of an image in individual blocks (or zones), with the ability to specify the size of black dots.

The FineReader Engine also offers a number of useful pre-processing functions, allowing to manipulate images such as "image scaling", "image clipping", "creating previews", "rotating (90, 180, 270 degrees)", "mirroring" and "inverting".

Document Analysis and Full Layout Retention

The document analysis function set of FineReader Engine API solves such tasks as automatic document conversion with full-page layout retention, zoning OCR with manually located blocks, etc. It includes:

• auto-detection of page orientation - 90, 180, 270 degrees (see above in Image Manipulation and Pre-processing);
• auto-detection of text blocks, tables, barcodes and pictures;
• auto-detection of vertical text in table cells;
• manual block zoning (adding, removing and editing blocks);

The unique FineReader Engine features are:

• Document Analysis for Archiving Tasks
  This function automatically detects and recognizes all text on documents including text embedded in pictures, charts, and diagrams. Developers may choose to use this mode of document analysis to extract exhaustive full-text information on documents needed for document index building (as in DMS, CMS, Archiving systems).
• Document Analysis for Invoices
  A special document analysis function designed as a preprocessing engine for converting semi-structured documents, such as invoices, payment drafts, checks, transfers, business cards, agreement, health claim forms, resumes, etc. In this preprocessing role, this function has been designed to find as much text on these documents as possible, including characters and numbers - even if this information is located within stamps, pictures, logos or small-text areas. Unlike in standard full-page document analysis, this specialized document analysis assumes all printed information on the documents is text. It also ensures that important text information is not identified as graphic elements and that words or numerical values are not separated into multiple characters. As a result, maximum information about the text, including its coordinates, is available for analysis, field-by-field processing and parsing at subsequent processing stages by other systems.
• Export to Multiple Formats including PDF, RTF/DOC/WordML, XML, and HTML with exact layout retention.

Recognition

OCR

• Recognize 190 languages for OCR.
• 170 languages with Latin, Cyrillic, Greek, Hebrew and Armenian characters
• 46 languages have dictionary/morphology support.
• Recognition of multilingual documents.
• Recognition of typewritten documents.
• Chinese, Japanese and Korean (CJK) Character Recognition (see more detailed information about CJK OCR in "Licensing Policy, add-on modules" section).
• Fast mode recognition.
  Designed for high-volume document processing applications where speed is more important than accuracy. This mode increases processing speed by 200-250%, making it particularly useful with document management and archiving systems.
• Recognition of OCR-A, OCR-B, MICR (E13B), and CMC7.
• FineReader XIX.
        There are many old documents, books, and newspapers published in the 17-20th century all over the world. The set of functions called as "FineReader XIX" of ABBYY FineReader Engine provides a UNIQUE capability to recognize texts published in the period from 1600 till 1937 in English, French, German, Italian, and Spanish. FineReader XIX supports special fonts such as Fraktur, Schwabacher and the majority of Gothic fonts.

Entire list of supported OCR languages see in "Specifications" section.
Barcode Recognition

    * Recognition of 1D barcodes.
      For the full list of supported barcode types, see the Specifications.
    * 2D barcode recognition (PDF417).
      The 2D Barcode recognition recognizes PDF417, the industry standard for 2D barcodes. PDF417 encodes up to 1.1 kilobytes of data, including text and graphics information.
    * Fast barcode extraction.
      This feature enables automatic finding and recognizing barcodes at any angle on a document. It works both for 1D and 2D barcodes.

Field-level/Zonal Recognition Support

The SDK provides powerful field-level/zonal recognition capabilities ensuring accuracy and speed enhancement on small fields/zones. This functionality is crucial for processing tasks like data extraction, key-word indexing, and keyword classification. Key functionality for field level or zonal recognition includes multilingual OCR and barcode recognition, including:

    * Definition of field content by setting alphabets and dictionaries.

    * Detection of in-filed spacing - Detection and recognition of fields where the spaces are allowed. The FineReader Engine 8.0 also allows use of dictionaries which contain word-combinations with spaces.

    * Text block despeckle, with the ability to specify the size of white or black «garbage».

    * External recognition tuning features - Provides integrators with multiple word-level and character-level hypothesis and allowing integrators to influence the hypothesis choice by inserting additional ranking criteria during the recognition process. 

PDF Conversion

The SDK includes powerful PDF conversion technology with extensive functions for PDF input and output including:

PDF Input

• Fast and accurate PDF processing. Analyses of internal information within the source PDF files such as annotations, metadata, text objects, font dictionaries and content streams and as a result enhances PDF performance and speed by efficient and accurate selection. When the text is embedded, examines the integrity of the text layer, and makes a decision as to whether or not to extract the text or apply OCR on a block by block basis.
• Capture of Internal PDF Information, extracting internal PDF links, hyperlinks and document properties such as: subject, author, title, and keywords.

PDF Output

• PDF Security and Encryption Support:
• The SDK supports a variety of PDF security settings, increasing its applicability for government agencies and other organizations demanding high security.
            o "Open File" password settings designed to prevent unauthorized access to a document.
            o Restriction of certain operations, such as printing, editing or extracting file content, by assigning permission passwords.
            o Support for the latest encryption standards.

    * Output in tagged PDF format - that can be "reflowed" to fit different page or screen widths. Ideal for use with handheld devices (PDAs) or screen readers typically used by visually impaired users.
    * Page size - Ability to set the size for all pages of a output PDF file.
    * Links in PDF files - Re-creates hyperlinks within a PDF file.

Superior Accuracy - With the award-winiing ABBYY recognition technologies, the FineReader Engine provides unmatched accuracy widely appreciated by many customers and industry professionals.

Multilingual OCR - With its multilingual OCR support, the SDK allows developers to create truly international solutions. It supports 189 OCR languages including Latin, Greek, Armenian, Cyrillic alphabets, as well as Chinese, Japanese and Korean. The ABBYY FineReader Engine delivers the same accuracy for documents with mixed languages.

Comprehensive SDK - The Engine provides a single, flexible platform for different document recognition and conversion tasks. It is the only solution in its class with a wide range of full-page and field-level/zonal recognition functions.

Easy Integration - For rapid and easy integration, the SDK provides a set of programming samples which allows developers and integrators to save their time and effort. ABBYY FineReader Engine 8.0 EPS offers complete access to low-level OCR functionality, which is available via an API (Application Programming Interface). For rapid integration, specialists also may use a popular CLI (Command Line Interface) to access the majority of its functions.

Multiple Platform Support - This version of ABBYY FineReader Engine supports Linux and FreeBSD platforms. In addition, ABBYY's technical team offers special services for porting recognition technologies to other platforms.

Flexible Architecture and Lisensing Scheme - The Engine's modular approach to architecture and licensing allows developers to choose the only functions they need while providing them with the ability to add additional functions quickly.

OCR Languages

ABBYY FineReader Engine 8.0 with Extended Platform Support recognizes 190 OCR languages including:

• 38 main languages with Latin, Cyrillic, Greek, Hebrew and Armenian characters, for which FineReader Engine provides dictionary support:
        Armenian (Eastern, Western, Grabar), Bulgarian, Catalan, Croatian, Czech, Danish, Dutch (Netherlands and Belgium), English, Estonian, Finnish, French, German (new and old spelling), Greek, Hebrew, Hungarian, Italian, Latvian, Lithuanian, Norwegian (Nynorsk and Bokmal), Polish, Portuguese (Portugal and Brazil), Romanian, Russian, Slovak, Spanish, Swedish, Tatar, Turkish and Ukrainian.
• 132 additional languages with Latin, Cyrillic or Greek characters:
        Abkhaz, Adyghian, Afrikaans, Agul, Albanian, Altai, Avar, Aymara, Azerbaijani (Cyrillic), Azerbaijani (Latin), Basque, Belarusian, Bemba, Blackfoot, Breton, Bugotu, Buryat, Cebuano, Chamorro, Chechen, Chukchee, Chuvash, Corsican, Crimean Tatar, Crow, Dakota, Dargwa, Dungan, Eskimo (Cyrillic), Eskimo (Latin), Even, Evenki, Faeroese, Fijian, Frisian, Friulian, Gagauz, Galician, Ganda, German (Luxemburg), Guarani, Hani, Hausa, Hawaiian, Icelandic, Ingush, Irish, Jingpo, Kabardian, Kalmyk, Karachay-balkar, Karakalpak, Kasub, Kawa, Kazakh, Khakass, Khanty, Kikuyu, Kirghiz, Kongo, Koryak, Kpelle, Kumyk, Kurdish, Lak, Latin, Lezgi, Luba, Macedonian, Malagasy, Malay, Malinke, Maltese, Mansi, Maori, Mari, Maya, Miao, Minangkabau, Mohawk, Moldavian, Mongol, Mordvin, Nahuatl, Nenets, Nivkh, Nogay, Nyanja, Ojibway, Ossetian, Papiamento, Provencal, Quechua, Rhaeto-Romanic, Romany, Rundi, Russian (old spelling), Rwanda, Sami (Lappish), Samoan, Scottish Gaelic, Selkup, Serbian (Cyrillic), Serbian (Latin), Shona, Somali, Sorbian, Sotho, Sunda, Swahili, Swazi, Tabasaran, Tagalog, Tahitian, Tajik, Tok Pisin, Tongan, Tswana, Tun, Turkmen, Tuvinian, Udmurt, Uigur (Cyrillic), Uigur (Latin), Uzbek (Cyrillic), Uzbek (Latin), Welsh, Wolof, Xhosa, Yakut, Zapotec, Zulu.
• 4 East Asian languages (with dictionary support):
        Traditional Chinese, Simplified Chinese, Japanese and Korean.
• FineReader XIX module for recognition of Fraktur/Black Letter texts written in 5 old European languages including English, French, German, Italian and Spanish (with dictionary support).
• 4 artificial languages:
        Esperanto, Interlingua, Ido and Occidental.
• 6 programming languages:
        Basic, C/C++, COBOL, Fortran, JAVA and Pascal.
• Simple chemical formulas
• Digits
• Tools for creating user-defined languages

Barcode Types

• 1D: Check Code 39, Check Interleaved 25, Code 128, Code 39, EAN 13, EAN 8, Interleaved 25, CODABAR (without checksum), UCC Code 128, Code 2 of 5 (Industrial, IATA, Matrix), Code 93, UPC-A, UPC-E and Postnet.
• 2D: PDF 417.

Supported Operating Systems

ABBYY FineReader Engine 8.0 has been tested on the following operating systems:

1) Linux

32-bit versions

• Red Hat Enterprise Linux 4 ES/AS, 5
• Fedora Core 5, 6
• Fedora 7, 8
• SUSE Linux 10.0
• openSUSE 10.2
• White Box Enterprise Linux 4 Respin 1, Respin 2
• Debian GNU/Linux 3.1, 4.0
• Ubuntu 6.06 LTS, 7.10

64-bit versions

• Red Hat Enterprise Linux 4.5, 5.1
• Fedora 7, 8
• openSUSE 10.3
• White Box Enterprise Linux 4 Respin 1
• Debian GNU/Linux 4.0r3
• Ubuntu 6.06 LTS, 7.10

2) FreeBSD 6.1, 6.2

In addition, ABBYY offers professional services to adapt the software to other platforms.

Supported Image Formats

Format	Extension	Open	Save
BMP: uncompressed black and white, uncompressed gray, uncompressed color	bmp	+	+
DCX: 2-bit - black and white 4- and 8-bit - gray TrueColor	dcx	+
PCX: 2-bit - black and white 4- and 8-bit - gray	pcx	+	+
PCX: TrueColor		+
PNG: black and white, gray, color	png	+	+
JPEG 2000: gray, color	jp2, j2c	+	+
JPEG: gray, color	jpg, jpeg, jfif	+	+
PDF (Version 1.6 or earlier)	pdf	+	+
TIFF: black and white - uncompressed, CCITT3, CCITT4, Packbits, ZIP gray - uncompressed, Packbits, JPEG, ZIP TrueColor - uncompressed, JPEG, ZIP multi image TIFF	tif, tiff	+	+
TIFF: black and white - CCITT3FAX, LZW gray - LZW palette - uncompressed, Packbits, ZIP TrueColor - LZW	tif, tiff	+
GIF: black and white - LZW-compressed gray - LZW-compressed TrueColor - LZW-compressed	gif	+

 

Export Formats

RTF, DOC, WordXML, XML, XLS, HTML, PDF, PDF Image Only, DBF and TXT/CSV.

Message Languages

Error and other messages are available only in English.

System Requirements

PC with Intel® Pentium® 300 MHz or higher processor.
Memory: 128 MB RAM for Runtime License installation and 512 MB RAM for Developer License installation.
Hard disk space: 700 MB for full installation and 70 MB for program operation.

With FineReader Engine for Embedded OS, ABBYY offers:

• Highly portable, small-footprint SDK with low requirements for system resources to integrate OCR and document conversion functions into MFPs and other intelligent devices;
• Professional customization service for hardware manufactures to smoothly adjust powerful ABBYY's technologies to various vendors' needs and embed additional features.

The SDK delivers ABBYY's core recognition technologies to convert scanned documents into searchable and highly compressed document formats: PDF, PDF/A and PDF with MRC.

Export to editable document formats: RTF, DOC/DOCX, XLS/XLSX, PPT/PPTX, TXT/CSV, DBF, XML is available for custom solutions.

ABBYY renders a special service for hardware manufactures enabling them to equip their products with a customized set of functions by integrating FineReader Engine for Embedded OS into MFPs and other devices.

High Accuracy of Document Recognition and Conversion

he SDK is based on ABBYY's OCR and PDF conversion technologies widely recognized by users and professionals for matchless accuracy of text recognition and superior conversion quality. For more information, please see ABBYY's awards and reviews


Low Requirements for Computing Resources

The OCR SDK for Embedded OS is optimized to work with strictly limited computing resources, including small memory size and low-power processors. It can be integrated into MFP and other imaging devices, various portable devices such as scanning pens, automated mail processing systems and more.

Memory requirements:

• 2-2.5 MB for library;
• 0.5-1 MB for dictionaries of each used recognition language;
• 1-10 MB or more for program operation (depending on the image size, colority and quality: 1-5 MB for small photo pictures, about 10 MB for A4 sized business letter).

For more information, please visit OCR SDK for Embedded OS - Technical Specifications or contact ABBYY team


Integration into Virtually Any Platform

The new OCR SDK can be ported to various embedded operating systems and CPU types and easily modified to support any new platform according to customer request.

To check if your platform is supported, please contact ABBYY team


Flexible Expandability and Customization

Depending on particular customer requirements, FineReader Engine for Embedded OS can be extended with any feature available in other ABBYY's SDKs such as FineReader Engine and FlexiCapture Engine.

This OCR SDK can be enhanced with additional set of technologies including:

• Intelligent character recognition (ICR)
• Optical mark recognition (OMR)
• Optical barcode recognition (OBR)
• Business card recognition (BCR)
• Document classification and indexing
• Data capture

For more information about additional features contact ABBYY team


Extensive Language Support

The OCR SDK for Embedded Systems delivers recognition of documents in 60 languages and provides dictionary support for 23 languages. Additional languages, from the total set of 195 languages for OCR already supported by ABBYY products, including various languages with Latin and Cyrillic alphabets, Chinese, Japanese, Korean, Thai, Hebrew and more, can be also included upon request.

For more information, please visit OCR SDK for Embedded OS - Technical Specifications or contact ABBYY team

Supported CPU and Operating Systems

ABBYY FineReader Engine for Embedded OS is compatible with many hardware and operating systems.

CPU types support

• x86
• xARM
• xPowerPC
• xand others

Operating systems support

• Windows for x86 processors
• Windows CE
• Linux
• VxWorks
• FreeBSD
• LynxOS
• and others

Development Platform
C/C++

Storage Memory Requirements (RAM/ROM)

• 2-2.5 MB for library (depending on the specific library version);
• 0.5-1 MB for dictionaries of each supported recognition language.
• The library can be stored either in ROM or in RAM depending on the specific device.

Runtime Memory Requirements (RAM)

• 2-2.5 MB for library (copied from the storage memory);
• 0.5-1 MB for dictionaries of each used recognition language;
• 1-10 MB or more for program operation (depending on image size, colority and quality: 1-5 MB for small photo pictures, about 10 MB for A4 sized business letter)

Supported OCR languages

23 languages with dictionary support:


Bulgarian, Czech, Dutch, Dutch Belgian, English, Estonian, Finnish, French, German, German New Spelling, Greek, Indonesian, Italian, Norwegian Bokmal, Norwegian Nynorsk, Polish, Portuguese, Portuguese Brazilian, Russian, Spanish, Swedish, Turkish, and Ukrainian.



37 languages without dictionary support:


Afrikaans, Albanian, Basque, Breton, Byelorussian, Catalan, Chechen, Crimean Tatar, Croatian, Fijian, Hawaiian, Hungarian, Icelandic, Indonesian, Irish, Kabardian, Latin, Latvian, Lithuanian, Macedonian, Malay, Maori, Moldavian, Mongol, Ossetic, Provencal, Rhaeto Romanic, Romanian, Samoan, Serbian, Slovak, Slovenian, Swahili, Tagalog, Tatar, Welsh, and Yiddish.



More than 130 other languages can be added upon request - contact ABBYY team


Supported import and export formats

Import formats: BMP, TIFF CCITT 4 Additional import formats for customized solutions: PDF, PCX, DCX, JPEG, JPEG 2000, TIFF, multi image TIFF, GIF

Export formats: TXT, PDF, PDF/A, PDF with MRC Additional export formats for customized solutions: RTF, DOC/DOCX, XLS/XLSX, PPT/PPTX, HTML, TXT/CSV, DBF, XML

Support for any other formats can be provided upon request - contact ABBYY team

Why this offer is interesting?

After many years of development and research in document conversion technologies, leveraging its vast experience of working with the world leading MFP manufactures, ABBYY now offers the complete line of solutions covering the needs of MFP vendors in OCR, PDF conversion and other related technologies.

ABBYY's recognition technologies have been appreciated by MFP users worldwide. Millions of customers use ABBYY FineReader Sprint, an OCR solution which is bundled with scanners and MFPs from the leading manufactures. ABBYY successfully accomplished a range of projects for embedding OCR technologies into MFP and scanning devices from global vendors.

ABBYY really knows MFP vendors' needs and is able to provide the most efficient solution!

ABBYY products for MFP integration

• ABBYY FineReader Engine for Embedded OS - A highly portable small-footprint SDK for systems with limited computing power and memory recourses. It is designed for porting recognition technologies to mid- and top-priced MFPs and can be customized for optimal functionality and performance.
• ABBYY FineReader Engine 9.0 - A powerful and versatile SDK for comprehensive systems. It can be integrated into top MFP models to provide the supreme OCR accuracy and maximum functionality.
• ABBYY Recognition Server 2.0 - A robust and powerful server-based solution for automating document recognition and PDF conversion of mid-to-high volumes of documents., With its powerful document management functionality and strong integration capabilities, this standalone server solution is an essential component for enterprise content management (ECM) and document management systems.
• ABBYY TouchTo - A touch-based metadata extraction technology for devices with LCD touch screens that routes data directly to backend. MFP with TouchTo embedded is a complete front-end data capture system for quick and accurate data transfer from paper documents to ERP and other enterprise systems.

ABBYY's customization service

ABBYY offers its professional embedding services based on strong experience in developing customized solutions for leading MFP vendors. For more information, please contact ABBYY team

Most business documents, especially price lists, contracts, or surveys consist of several pages. With this Data Capture toolkit, you get the unique technology to easily process documents with multiple pages and tables that stretch over more than one page.

ABBYY FlexiCapture Engine 8.0 extracts important data from documents like invoices, contracts, or letters which have no fixed layout. Despite the fact that invoices may have different structures, the necessary fields such as contract number, position name, or signature can be quickly located and extracted in an appropriate format.

The toolkit offers effective and convenient instruments for checking the validity of captured data and tracking recognition errors:

• If needed, recognized data are automatically checked to determine if they satisfy certain conditions. This covers comparison with a known value (e.g., supplied as a regular expression or taken from a data base), comparison of data items against one another, or checking if data falls within pre-defined boundaries. Finally, scripts can be used to create very flexible rules.
• Extremely effective Group Verification allows reviewing similar looking symbols all together. This feature speeds up manual verification and reduces the number of human-related errors.

Thanks to the world's largest language base and high-quality OCR, ABBYY FlexiCapture Engine 8.0 is able to index a document with relevant data and convert it to PDF or PDF/A.

ABBYY FlexiCapture Engine 8.0 provides a single entry point to automatically extract valuable data from the stream of forms and documents. The documents in the bundle can vary in structure and type, but they will be precisely classified based on pre-defined templates. Thus, document sorting and templates matching are performed without any manual labor.

ABBYY FlexiCapture Engine 8.0 makes use of all ABBYY's achievements in processing documents with fixed layouts like questionnaires or tests. Should your customers conduct a survey, or use a pre-defined set of financial forms, they can rely on highly accurate ICR and OMR technologies provided with the toolkit.

ABBYY FlexiCapture Engine 8.0 makes use of the huge language base of more than 180 languages for OCR and more than 110 languages for ICR.

The Engine enables you to easily add functionality required from today's document management solutions, e.g.:

• Automated data extraction from various types of fixed documents like questionnaires or insurance forms, which often come in large numbers;
• Handling semi-structured forms in which the location of key data fields (such as date, invoice number, or text block) varies across documents, providing fast and precise data extraction;
• Document indexing and classification options allow you to automate document storage and archiving routines. This makes digital documents, even unstructured ones, easily accessible and improves the entire document workflow.

ABBYY's reputation and high profile in the industry will help in promoting your solutions.

ABBYY's form processing and data capture end-user products are used by many government agencies and commercial organizations all over the world, including: Allgemeiner Deutscher Automobil-Club e.V. (Germany), Connecticut Braille Association (USA), UMW Toyota (Malaysia), Cargill Foods (USA), Indian Educational Institutions (India), Finansbank (Turkey), Lithuanian Tax Inspectorate (Lithuania), Ministry of Education of the Russian Federation (Russia), Trendset (USA), Ministry of Rural Development of Malaysia (Malaysia), Prodco TV (UK) and many more.

In today's world, it is very important to have not only a local version of a product but to be ready to make localized international solutions. The Engine has a unique OCR/ICR language coverage and other features you may need:

FlexiCapture Engine is able to recognize more than 180 languages in OCR (including the Latin, Greek, Armenian, Cyrillic, and Thai alphabets) and more than 110 languages in ICR. The ABBYY team is constantly working to increase the list of available languages, both with and without dictionary support.

Applications built on the Engine, offer automatic processing of incoming documents, simplifying input, recognition, verification, and export into just one action performed on a bundle of records. The whole process can be configured for operating in standalone mode for maximum stability and smoothness.

Applications powered by ABBYY FlexiCapture Engine cut down expenses on labor force and related risks. They help you to save hours of employees' work on inputting and re-inputting data if they were incorrectly recognized. All this is possible due to:

• the high quality of OCR and ICR that reduces the amount of data correction work;
• rule-based automated verification process;
• extremely effective error-proof group verification.

ABBYY is constantly developing existent and searching for new technologies that respond to every day challenges faced by end-users. FlexiCapture 8 is offers multiple examples of radical improvements:

• New and emerging approach handling a document not as just a bundle of pages but as a single entity with uniform processing options for every page;
• Export of images along with extracted data for classifying and indexing purposes;
• Support for recurrent items in documents, including complex tables, to speed up processing of groups of identical fields.

ABBYY FlexiCapture Engine 8.0 delivers a full-range of state-of-the-art technologies for data capture and archiving scenarios. This allows developers to stick to one SDK supplier for different tasks, having a single approach to developing, maintenance, and training for the SDK.

ABBYY provides not only traditional data capture utilities but also instruments for document conversion. These tasks are highly interconnected and the customer benefits from having only one supplier for all of them.

FlexiCapture Engine 8.0 has a clear and easy-to-use API. Nevertheless, to shorten the learning curve the distribution package contains:

• Training courses and certification questions on ABBYY FlexiCapture technology
• Professional Services to help you quick-start your development
• Single and integral API;
• Full and clear developer's Help.

The Engine API conforms to the COM standard and can be easily used in C/C++, Visual Basic, .Net, Delphi, or any other development tools supporting COM components.

With minimum effort, the Engine can be adopted for use in scripting languages such as VBS, JS, and Perl.

The distribution package contains samples for C/C++, VB 6, VB.Net, C#, and Delphi programming languages.

ABBYY is an international company with a wide geography of local offices ready to provide you with technical support:

• At the time which is most convenient to you, as we are able to respond during your office hours;
• In many cases in a language you are familiar with;
• With a minimum response time, since we provide technologies we are developing ourselves.

OCR

ABBYY FlexiCapture Engine 8.0 recognizes more than 190 OCR languages, including:

• 37 main languages with Latin, Cyrillic, Greek or Armenian characters, for which FineReader Engine provides dictionary support: Armenian (Eastern, Western, Grabar), Bashkir, Bulgarian, Catalan, Croatian, Czech, Danish, Dutch (Netherlands and Belgium), English, Estonian, Finnish, French, German (new and old spelling), Greek, Hungarian, Indonesian, Italian, Latvian, Lithuanian, Norwegian (Nynorsk and Bokmal), Polish, Portuguese (Portugal and Brazil), Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Tatar, Turkish and Ukrainian
• 133 additional languages with Latin, Cyrillic or Greek characters: Abkhaz, Adyghian, Afrikaans, Agul, Albanian, Altai, Avar, Aymara, Azerbaijani (Cyrillic), Azerbaijani (Latin), Basque, Belarusian, Bemba, Blackfoot, Breton, Bugotu, Buryat, Cebuano, Chamorro, Chechen, Chukchee, Chuvash, Congo, Corsican, Crimean Tatar, Crow, Dakota, Dargwa, Dungan, Eskimo (Cyrillic), Eskimo (Latin), Even, Evenki, Faeroese, Fijian, Frisian, Friulian, Gagauz, Galician, Ganda, German (Luxemburg), Guarani, Hani, Hausa, Hawaiian, Icelandic, Ingush, Irish, Jingpo, Kabardian, Kalmyk, Karachay-balkar, Karakalpak, Kasub, Kawa, Kazakh, Khakass, Khanty, Kikuyu, Kirghiz, Koryak, Kpelle, Kumyk, Kurdish, Lak, Latin, Lezgi, Luba, Macedonian, Malagasy, Malay, Malinke, Maltese, Mansy, Maori, Mari, Maya, Miao, Minangkabau, Mohawk, Moldavian, Mongol, Mordvin, Nahuatl, Nenets, Nivkh, Nogay, Nyanja, Ojibway, Ossetian, Papiamento, Provencal, Quechua, Rhaeto-Romanic, Romany, Rundi, Russian (old spelling), Rwanda, Sami (Lappish), Samoan, Scottish Gaelic, Selkup, Serbian (Cyrillic), Serbian (Latin), Shona, Somali, Sorbian, Sotho, Sunda, Swahili, Swazi, Tabasaran, Tagalog, Tahitian, Tajik, Tok Pisin, Tongan, Tswana, Tun, Turkmen, Tuvinian, Udmurt, Uigur (Cyrillic), Uigur (Latin), Uzbek (Cyrillic), Uzbek (Latin), Welsh, Wolof, Xhosa, Yakut, Zapotec, Zulu
• 4 artificial languages: Esperanto, Interlingua, Ido and Occidental

ICR

ABBYY FlexiCapture Engine 8.0 provides ICR for 112 languages, including:

• 28 languages with morphology/dictionary support (languages with Latin characters, 3 Cyrillic languages and Greek)
• 84 languages without dictionary support
• Supports 22 styles of hand-writing of different countries and areas: European, American, Canadian, Russian, Japanese, Arabic and Thai.

• PDF:
  Files in PDF format (Version 1.6 or earlier)
• BMP:
  uncompressed black and white, uncompressed gray, uncompressed color
• PCX, DCX:
  2-bit - black and white 4- and 8-bit - gray TrueColor
• JPEG:
  gray, color
• JPEG 2000:
  grey, 8-bit color, RGB or Y?? colorspace, 8 bit per channel color, encoded using 8-bit palette in RGB colorspace
• TIFF:
  black and white - uncompressed, CCITT3, CCITT3FAX, CCITT4, Packbits, ZIP, LZW gray - uncompressed, Packbits, JPEG, ZIP, LZW TrueColor - uncompressed, JPEG, ZIP, LZW Palette - uncompressed, Packbits, ZIP multi image TIFF
• GIF:
  black and white - LZW-compressed gray - LZW-compressed TrueColor - LZW-compressed
• PNG:
  black and white, gray, color
• DjVu:
  black and white, gray, color

Dialogue captions, text, error and other program messages are available in English, German, French, Spanish, Portuguese (Brazil), Russian, Polish, Czech, and Hungarian.

• XLS
• DBF
• CSV
• TXT
• PDF and PDF/A
• XML

1D Barcodes:

1. Codabar
2. Code 128
3. Code 39
4. Code 93
5. EAN 8
6. EAN 13
7. IATA 2 of 5
8. Industrial 2 of 5
9. Interleaved 2 of 5
10. Matrix 2 of 5
11. PostNet
12. UCC-128
13. UPC-A
14. UPC-E

1D Barcodes with checksum:

1. Code 39
2. Interleaved 2 of 5
3. Codabar

1D Barcodes with supplemental: :

1. EAN 8
2. EAN 13
3. UPC-E

2D Barcodes: :

1. PDF417

• Microsoft Visual Studio .NET 2003
• Microsoft Visual Studio 2005
• Microsoft Visual Studio 2008
• Microsoft Visual Basic 5.0, 6.0;
• Microsoft Visual C++ 4.x and above;
• VB Script, and other scripting languages;
• Borland Delphi 2.0 and above;
• Any other development environment that supports COM and ActiveX objects correctly.

Standalone Runtime or Developer License Installation :

• PC with Intel® Pentium®/Celeron®/XeonT, AMD K6/AthlonT/DuronT/SempronT or compatible processor with a minimum clock speed of 200 MHz
• Operating System: Microsoft® Windows Server® 2008, Windows Vista®, Windows Server 2003, Windows® XP, Windows 2000, and 64-bit versions of Windows Server 2008, Windows Vista, Windows Server 2003, Windows XP.
• Memory: 128 MB RAM.
• Hard disk space: 365 MB for full developer installation and 70 MB for program operation
• Video card and monitor (min. resolution 800×600)
• Keyboard, mouse or other input device
• The user must have read/write permissions to the following registry branches:
  o HKEY_CLASSES_ROOT
  o HKEY_LOCAL_MACHINE\Software\ABBYY
  o HKEY_CURRENT_USER\Software\ABBYY

Network Runtime Installation

Server Requirements

• PC with Intel Pentium/Celeron/Xeon, AMD K6/Athlon/Duron or compatible processor. Processor must be 200 MHz or higher
• Operating System: Microsoft Windows Server 2008, Windows Vista, Windows Server 2003, Windows XP, Windows 2000, and 64-bit versions of Windows Server 2008, Windows Vista, Windows Server 2003, Windows XP.
• 10 MB of free hard-disk space

Workstation Requirements

Server Requirements

• PC with Intel Pentium/Celeron/Xeon, AMD K6/Athlon/Duron/Sempron or compatible processor with a minimum clock speed of 200 MHz
• Operating System: Microsoft Windows Server 2008, Windows Vista, Windows Server 2003, Windows XP, Windows 2000, and 64-bit versions of Windows Server 2008, Windows Vista, Windows Server 2003, Windows XP.
• Memory: 128 MB RAM.
• Hard disk space: 365 MB for library and 70 MB for program operation
• Video card and monitor (min. resolution 800x600)
• Keyboard, mouse or other input device
• The following registry branches should be accessible from the workstation: o HKEY_CLASSES_ROOT - full control access
  o HKEY_LOCAL_MACHINE\Software\ABBYY - full control access
  o HKEY_CURRENT_USER\Software\ABBYY - full control access
  o HKEY_CLASSES_ROOT\CLSID - full control access
  o HKEY_CLASSES_ROOT\TypeLib - full control access for installation and activation only
• The following folders should be accessible from the workstation:
  o %TEMP% folder - full control access
• The following components should be installed:
  o Microsoft® Internet Explorer 5.0 or higher

With its highly scalable distributed architecture, ABBYY Recognition Server is very efficient in high-volume OCR and document conversion.

The main components of ABBYY Recognition Server 3.0 include Server Manager, a central unit designed for system management, and Processing Stations, which perform OCR and document conversion. One Server Manager can control a virtually unlimited number of Processing Stations connected to it. It effectively distributes all recognition and conversion tasks among the Processing Stations and CPUs, balancing the workload across the system resources. By connecting dozens of Processing Stations to the server, you can increase the throughput to several hundred pages per minute.

ABBYY Recognition Server 3.0 can save documents in archive-friendly formats, such as TIFF, XML and PDF. PDF files created by the program comply with the PDF/A standard for long-tem preservation. Advanced MRC compression helps to achieve significantly smaller file sizes without any visible loss in quality.

ABBYY Recognition Server also offers a range of features aimed at making high-volume document conversion more productive yet cost-effective:

• Automated Document Conversion
  
  OCR and document conversion are automated and performed on back-end servers. By eliminating user involvement in the conversion process, ABBYY Recognition Server 3.0 significantly reduces the time spent on document processing.
• Advanced Scheduling
  
  The product provides advanced scheduling options for managing task priorities and controlling the load of the processing stations during a day or week. For instance, some workstations can be set up for round-the-clock operation, and others for night-time OCR processing, while in the daytime these workstations can be used to perform the usual office tasks. Thanks to these options, your company won't need to purchase unnecessary hardware and will be able to use the existing resources in the most efficient way.
• Easy Scanning and Sorting
  
  ABBYY Recognition Server 3.0 provides user-friendly interface for batch scanning, document separation, sorting and key indexing. Routine operations can be automated by using scripted rules, which tell ABBYY Recognition Server how to classify and index the document according to its content.

Effective document management is an essential part of any effective business. Many organizations have adopted document or content management systems for storing their documents and routing them throughout the organization's business processes. However, installing a CMS system is only part of the story, as it needs a supplemental tool to capture new documents that come every day from various entry points in the company.

ABBYY Recognition Server is a powerful yet convenient front-end to an ECM system. It offers an intuitive interface for scanning and indexing documents as well as an automated engine for converting those documents into a searchable format. The documents are classified, either automatically or by an operator, and routed to the appropriate destination based on their type and attributes. The product can also operate as a web service and supports remote document upload. Therefore its implementation is not restricted to one office but can serve several remote entry points at a time.

Feature highlights:

• Intuitive Scanning and Indexing interfaces
  
  ABBYY Recognition Server includes Scanning and Indexing Stations that allow operators to capture documents quickly and easily on their PCs. The stations have intuitive and user-friendly interfaces that will be clear to both a back-office assistant and a knowledge worker without prior training.
• Automated OCR and document conversion
  
  OCR and document conversion, the most resource-intensive part of the processing, are done automatically on the server back-end and requires no user involvement whatsoever.
• Compatible with different kinds of ECM systems
  
  ABBYY Recognition Server provides a ready-to-use connector to Microsoft SharePoint Server and flexible scripting capabilities for linking the software to virtually any ECM system. Various kinds of connectors can be created as Java or VB scripts.

OCR is only performed by certain users in a company and at certain times it can be done on users' own PCs. In the case of small- to medium-sized businesses, this "ad hoc" scenario can be implemented in a flexible and fast manner by installing ABBYY FineReader Professional Edition or ABBYY FineReader Corporate Edition.

For large organizations with hundreds or even thousands of employees converting a variety of different document types, this per-user installation is not suitable. Installing the desktop version would require significantly more effort involved in maintenance, administration, training and supervision. Moreover, the cost of licensing so many desktop versions may be unreasonably high.

The most efficient solution for large organizations in need of distributed OCR is to deploy a single, centralized OCR and document conversion service running on a server back-end. Employees can use the centralized OCR service on the network at any time, even outside normal business hours, and from any location. ABBYY Recognition Server is ideally suited for that purpose and offers a range of unique advantages:

• Round-the-clock availability of OCR service
  
  There is no need for an administrator to install the program on each workstation in the local area network. All the company's employees have access to the server-based OCR functionality automatically and at all times.
• Low-cost maintenance
  
  The installation, configuration and administration of ABBYY Recognition Server are easy and cost-efficient because these operations are performed on a single server rather than on many desktop computers.
• No special training is required
  
  Users of ABBYY Recognition Server don't need to have any knowledge of OCR technology at all. All they need to know about the program is where to send a document in order to get its recognized version back.
• OCR available even for remote workers
  
  ABBYY Recognition Server supports remote access via e-mail and the Web and therefore can be accessible to users not only from within the local area network but from remote computers as well (e.g. from an employee's home PC, or from a laptop during a business trip).
• Easy integration with all kinds of MFPs
  
  An administrator can easily associate ABBYY Recognition Server with all network scanners and MFPs in the company's IT infrastructure. Thus, wherever employees scan documents, they will always be able to have them converted into a DOC or PDF format right away.

Search for information is a vital part of any office workflow. As the organization grows, documents scatter across departments, file folders and ECM system, and search takes more and more valuable time Microsoft® offers effective instruments to organize enterprise search on different levels, from centralized content storages to individual desktops. Microsoft Office SharePoint Server has powerful search capabilities in SharePoint document libraries and folders; Windows Search is helpful in finding files on desktop computers.

ABBYY Recognition Server IFilter is a powerful add-on to these engines that enables them with capability to search through full content of image documents. Normally search engines can index full text only in document file formats like HTML, RTF, DOC, XLS etc. In reality, a lot of important information is contained in image files, such as JPEGs, or highly popular PDFs and TIFFs, and remains invisible for conventional search engines. Scanned and photographed documents, invoices, letters, contracts - all these documents can be retrieved only using the file name, but not using the actual content of the document. To extend full-text search over image documents and leave no important knowledge undiscovered, OCR functionality is a must.

ABBYY Recognition Server with its OCR IFilter component is exactly the right solution: it "unlocks" the content of image documents by means of OCR and makes it available for indexing by SharePoint Server and Windows Search. With ABBYY Recognition Server IFilter, the document search in the organization becomes truly encompassing.

How it works

ABBYY Recognition Server is integrated with Microsoft Office SharePoint Server and Windows Search as described below:

1. ABBYY Recognition Server is installed on a server computer (which may be separate from the SharePoint hosting machine). A special component, ABBYY Recognition Server IFilter, is installed on top of the SharePoint Server and/or user desktops to provide communication between the search system and the Recognition Server. The IFilter is a light component which consumes almost no computer resources and does not affect the response time of the SharePoint Server;
2. Microsoft SharePoint (or Windows Search) crawler traverses the libraries (or computer folders) searching for new documents that need to be indexed. Each ABBYY IFilter receives image documents from the corresponding crawler and passes them to ABBYY Recognition Server;
3. ABBYY Recognition Server automatically performs high-quality OCR on the images and sends the recognized text back to the IFilter;
4. Microsoft search engine accepts the document contents from ABBYY IFilter and builds an index. The image then becomes discoverable via full-text search.

With Microsoft Office SharePoint Server:

With Windows Search:

Solution Benefits

• "Unlocks" images in SharePoint Servers and on user desktop computers. A single installation of ABBYY Recognition Server will OCR images from all computers and SharePoint Servers in the corporate network.
• Supports various image formats. A single ABBYY IFilter will take care of images in all kinds of image formats from JPEG to TIFF, PDF and DjVu.
• Recognizes documents in all languages. ABBYY Recognition Server is based on the award-winning ABBYY OCR technology which supports more than 190 languages, can process multi-lingual documents and provides superior quality ensuring that no documents are left out from search.
• Powerful OCR on a dedicated server. ABBYY Recognition Server can be installed on a dedicated server computer so that the resource-intensive OCR module is separated from the SharePoint Server and desktop computers and doesn't affect their productivity and work. In case of a large image backlog, ABBYY Recognition Server can be easily scaled up by plugging additional OCR stations that will share the workload automatically.
• Takes care of all kinds of OCR tasks. ABBYY Recognition Server usage is not limited to integration with Microsoft search. The product can also be used as a full-scale OCR and document conversion server for all kinds of tasks, from converting a scanned document to Word to creating searchable PDF archives.

Integrated with the Goggle Search Appliance, ABBYY Recognition Server significantly expands its capabilities to efficiently search information in distributed document storage systems and archives across the entire enterprise.

Finding necessary information scattered across different departments and electronic document storage in a large organization can be a real challenge unless you use an enterprise search system like the Google Search Appliance. The Google Search Appliance indexes documents in various storage locations and resources across the enterprise so that people can quickly find any document by keywords. However, a lot of valuable information is typically stored in the form of images (such as scanned PDF files) and therefore is inaccessible to indexing and search engines.

Why ABBYY Recognition Server

ABBYY Recognition Server processes document images to make them searchable. It recognizes images by applying optical character recognition (OCR) technology, transforms images into text, and sends the output to the search system together with links to the original documents. As a result, image documents stored in corporate file shares become available for full-text search.

How It Works

Working in conjunction with the Google Search Appliance, ABBYY Recognition Server monitors specified network file shares, picks image files from them, and performs OCR on them. Then it submits the recognized text to the search system in an XML feed along with links to the original images.

The text from the feed is included in the index. Now, if the user types a search query that contains a word from the text of the document, the image will turn up in the search results.

Benefits

ABBYY Recognitions Server brings additional benefits to the users of the Google Search Appliance and makes their search experience more fulfilling and efficient.

• No documents are left out. ABBYY Recognition Server crawls specified document storage resources and indexes all image content. Combined with the Google Search Appliance engine, it searches all documents in both text and image formats, leaving no valuable information overlooked.
• Accurate search results ensured by cutting-edge OCR technologies. ABBYY's award-winning OCR technologies used in Recognition Server ensure the accuracy of text extraction even when processing low-quality images, thus providing reliable search results.
• Multi-language search. ABBYY Recognition Server supports OCR in more than 190 languages and allows multi-language documents to be indexed correctly.
• Full-fledged OCR server at your service. ABBYY Recognition Server is a powerful OCR service available 24*7 for various document conversion tasks your company may encounter on a daily basis. Let Recognition Server enhance your business processes while performing background OCR for the Google Search Appliance at the same time.
• Scalable to any hardware configuration. ABBYY Recognition Server gives you full control of the CPU resources used for performing OCR. You can scale up the system capacity by adding more servers to boost the recognition speed, or limit the recognition process to certain CPU cores so that it does not interfere with other programs running on the server.

ABBYY Recognition Server covers all steps of document capture, from scanning to indexing and exporting documents to archiving and content management systems.

ABBYY Recognition Server has an intuitive interface and can be set up and operated without prior training.

ABBYY Recognition Server is known for its unmatched scalability. The solution is easily extendable to multi-core CPUs or multiple servers, and therefore able to cope with any volume of documents, processing them as scheduled or round-the-clock.

ABBYY Recognition Server will supplement your scanning devices and back-end software with powerful document capture functionality.

ABBYY Recognition Server connects as a background OCR server to enterprise systems such as Microsoft® Office SharePoint® Server, Windows® Search and Google Search ApplianceT, enhancing their capabilities to search over the content of document images.

ABBYY Recognition Server includes the well-known ABBYY OCR engine that delivers unprecedented recognition accuracy for any kind of documents. It supports Latin, Cyrillic, Asian and other writing systems, including Chinese, Japanese, Korean, Hebrew, Thai, and Vietnamese.

ABBYY Recognition Server consists of several components, which can be installed on the same or on different computers in a LAN. The main components are:

• Server Manager - a central service component, which controls the document processing queue and distributes the tasks among the stations
• Processing Station - a service that performs recognition and document conversion
• Scanning Station - a client station for batch scanning and image pre-processing
• Indexing Station - a client station for document classification and indexing
• Connector to Google Search Appliance™ (GSA) - a component that allows Google Search Appliance to use ABBYY Recognition Server for extracting content from document images
• Connector to Microsoft® Search Systems (IFilter) - a component that allows Microsoft Office SharePoint Server and Windows Search to use ABBYY Recognition Server for extracting content from document images
• Remote Administration Console - a client console used for configuring and monitoring Recognition Server

The document conversion process in Recognition Server can be divided into six logical parts:

Scanning Station

Scanning Station provides functionality for batch scanning and preparation of images for further processing:

• scanning via TWAIN, WIA and ISIS;
• quick image preview;
• image preprocessing (rotation, deskew, despeckle, etc.);
• document separation by barcodes / blank pages / fixed number of pages.

Import from network/FTP folders

ABBYY Recognition Server can automatically import images from the following network resources:

• network folder;
• FTP folder (e.g. if images are to be uploaded from remote locations);
• E-mail folder (e.g. if users send images for conversion by e-mail).

OCR is done on a Processing Station automatically. It is possible to connect several computers to the Server Manager as Processing Stations, and the Server Manager will balance the workload among these stations evenly. This will result in much faster processing of documents.

The OCR and barcode recognition technologies implemented in Recognition Server deliver unprecedented accuracy and support various types of text and the most popular 1D and 2D barcodes. The OCR process has extensive language support. The supported languages include 198 languages with Latin, Cyrillic, Greek and other scripts, Chinese, Japanese, Korean, Vietnamese, Hebrew, Yiddish, and Thai. European languages written in Gothic fonts are also supported.

To preserve the original document layout, ABBYY Recognition Server uses Adaptive Document Recognition Technology (ADRT). ADRT significantly improves document layout retention when saving documents to DOC and RTF formats. The logical structure of an entire document is reproduced, including headers, footers, footnotes, page numbers, table of contents linked to the document sections, and notes to pictures and diagrams.

Sometimes there is a need to process important documents which have to be recognized with exceptional accuracy. At the same time, the quality of the scans may not be perfect, suffering from low resolution and unwanted noise. In this case it is very important to have a reliable quality assurance mechanism.

Automatic quality control allows the administrator to set a threshold for recognition accuracy: documents with poor-quality text will not be converted, but rather stored in a separate folder for special treatment.

For images scanned in a batch, ABBYY Recognition Server offers several built-in document separation options: by blank sheets, barcode sheets, or barcodes stuck or printed on the first page of each document. Additional custom rules based on the recognized text can be created using scripting.

Document classification and indexing can be easily done with an intuitive Indexing Station that allows the operator to select a document type from the predefined list and fill in document attributes. If the attribute values are contained in the document itself, there is no need to type them in - the operator can simply outline the necessary section on the page, and the index field will be populated with the text.

Document type detection and indexing can be automated with Java or VB scripts.

ABBYY Recognition Server saves documents in a user-defined file format and delivers them to the network folder, e-mail address, SharePoint document library or to any other destination defined in the export script.

The program supports flexible rules for naming and routing output files. For instance, a document type and attributes can be used to name an output file or folder in the most convenient manner.

Recognition Server can convert images into various kinds of searchable or editable formats: PDF, PDF/A, RTF, TXT, DOC(X), XLS(X), XML and into popular image formats: TIFF, multi-page TIFF and JPEG.

Within the PDF creation functionality, Recognition Server offers an extended set of options:

• document security;
• enhanced MRC compression for creating small files while preserving their visual quality;
• Web optimization;
• tagged PDF files;
• adding headers, footers and Bates stamps into documents;
• creation of PDF files compliant with PDF/A standard.

Recognition Server is administered via a convenient interface based on the Microsoft Management Console. It allows the administrator to configure the system and monitor its activity: to set processing parameters, to manage licenses, stations, user permissions, processing queues, and to view logs.

With the priority management and scheduling features, the administrator can control the order in which the documents are processed and use the stations' hardware resources efficiently by scheduling OCR for night hours or weekends.

ABBYY Recognition Server provides an application programming interface (API) for integration with other applications. The API can be used to pass image files and processing parameters to Recognition Server, get notifications about job completion and obtain converted files.

The new Scanning Station offers an intuitive interface for high-speed production scanning via TWAIN, WIA, and ISIS drivers. Scanned batches can be sorted into documents and exported to network folders, FTP servers or directly to ABBYY Recognition Server workflows for further OCR and indexing.

TABBYY Recognition Server 3.0 introduces an Indexing Station that provides an intuitive user interface for specifying document types and attributes. The "rubber-band" indexing feature is fast and efficient: instead of typing the text in, the operator can simply outline the necessary areas on the page, and the attribute fields will be populated automatically.

With the new scripting functionality, document type detection and indexing may be done automatically based on the structure and content of a document.

ABBYY Recognition Server 3.0 introduces scripting functionality that allows the administrator to create more flexible rules for document separation. For example, a new document can be started whenever a certain word, phrase or barcode value occurs on a page.

The Server intelligently routes output documents based on their content and attributes. The documents can be delivered to file storage, e-mail addresses and ECM systems through an export script. A separate export handling script can be set up for dealing with failed jobs.

Integration with the Google enterprise search system from Google. In addition to the conventional indexing of text-based documents, it adds to the search system the ability to index the full text content of faxes, scanned agreements, correspondence, and any other TIFF, JPEG or PDF documents thus making them easily retrievable.

ABBYY Recognition Server 3.0 expands the capabilities of Microsoft® Office SharePoint® Server and Windows Desktop Search. The IFilter component enables the search systems to index the full text content of faxes, scanned agreements, correspondence, and any other TIFF, JPEG or PDF documents, thus making them easily retrievable.

ABBYY Recognition Server 3.0 includes a new ABBYY technology for Chinese, Japanese and Korean languages. Functionality enhancements include better accuracy, faster processing and the ability to combine the CJK languages with other languages (not only English).

These languages are new to the ABBYY Recognition Server product line:

1. Vietnamese
2. Yiddish
3. Latvian Gothic

ABBYY Recognition Server 3.0 expands the set of recognizable 2D barcodes now covering several most popular formats. New barcode types to appear in ABBYY Recognition Server 3.0 are:

1. Aztec
2. Data Matrix
3. QR Code

ADRT for precise document reconstruction - This is a new recognition technology based on an innovative set of document synthesis algorithms. It automatically builds a logical model of the document identifies its elements and decides on:

• the formatting role of elements such as headers ,footers, footnotes, page numbers, etc.
• the order in which the document should be read
• how the document's elements should be reconstructed

Thanks to ADRT, the structural parts and formatting elements of a document can be automatically identified and reproduced.