Recognition Server Functionality and Features

Key Features

Highly Accurate Recognition in 191 Languages
The award-winning ABBYY’s OCR technology delivers unprecedented recognition accuracy for any kind of documents.

Unattended Server-based Processing
Document conversion tasks are performed automatically on a server, during scheduled hours or round-the-clock.

Unmatched Scalability
With its ability to use resources of additional computers and CPUs during the processing, Recognition Server can convert virtually any volume of documents within the required timeframe. In addition, there is no need for complex system configuration – it takes just a few minutes to extend the processing power by plugging additional stations into the system.

Centralized Management
Recognition Server provides a remote management console as a central administration point for defining processing parameters, creating specific “workflows” for particular projects and managing recognition stations across the enterprise.

Reliability and Fault Tolerance
Designed as a highly robust solution, Recognition Server ensures ongoing system stability and data safety.

Flexible Integration Tools
Integration with scanners, MFPs, imaging applications and backend systems has never been easier. Recognition Server can communicate with other systems in a number of ways: via “watched” folders, email, COM-compatible API or Web Service API. The program provides all the features to function as an OCR Web Service in a Service-Oriented Architecture (SOA).

What’s New

New ABBYY Recognition Server 2.0 significantly extends the compatibility with different applications and platforms due to its ability to operate as OCR Web Service. The new version also enables seamless document output to Microsoft® SharePoint® Server and document conversion via email. In addition, Recognition Server 2.0 offers powerful features to increase the efficiency of large-scale document processing projects and extended format and language support.
New features of ABBYY Recognition Server include:

• New Interface Languages — The user interface and documentation are available in 5 new languages: German, French, Italian, Spanish and Russian.
  
• Web Service API — Enables Recognition Server to be used as a web service and makes it fully compatible with service-oriented architecture (SOA). The new OCR solution is able to communicate with applications on any platforms. The interaction with other applications is performed via HTTP, which enables integration of Recognition Server with remote applications and services over the Internet.
• Document Conversion via Email — With the added support for Microsoft Exchange Server, POP3 and SMTP email servers, Recognition Server is able to automatically process image attachments sent from email clients or network scanners and MFPs. Recognized documents can be sent back to the same user or to any other email addresses specified in the program settings.
  
• Export of Documents to Microsoft Office SharePoint Server — Output documents can be automatically stored in the SharePoint Server document library.
  
• Verification Station — Recognition Server is shipped with a new client station to execute verification of recognized text. The administrator can specify whether all recognized pages should be verified or only those pages with quality below a preset threshold. Verification permissions can be granted to every user or certain users only.
• Document Separation — Recognition Server supports several document separation methods for documents scanned in a batch. The document separation can be performed by fixed number of pages, by using blank separator pages and pages with bar codes. There is also a possibility to handle pages from each subfolder as a separate document.
  
• PDF/A Output — Recognition Server supports saving of documents in PDF/A–1b and PDF/A–1a formats, compliant with the modern standard for long-term document archiving.
  
• MRC PDF Compression Support — The new version delivers enhanced compression algorithm, based on Mixed Raster Content (MRC) image processing method, intended to reduce the size of PDF files while preserving their quality.
  
• DOCX and XLSX Output — Output to Microsoft Office 2007 formats is supported.
  
• DjVu Input Support — ABBYY Recognition Server now processes images in DjVu format.
  
• Thai Recognition Language — With Thai OCR language added, Recognition Server now supports 191 OCR languages in total.
  
• Support for Custom Dictionaries — Recognition of some professional terms and user-specific words can be enhanced by using a custom dictionary.
  
• Recognition with User Patterns — The recognition of documents printed in non-standard fonts or documents of low print quality can be improved by applying a user pattern. A user pattern is created by training the recognition engine to read the particular text type properly.
  
• Scheduling and Priority Setting for Processing Stations — The administrator can control the usage of hardware resources during a day or a week by scheduling the activity of the processing stations. The schedule can be set for individual stations or groups of stations. The administrator also can lower the priority of OCR processes on the particular processing stations, so that the stations can execute other tasks smoothly while performing OCR in a background mode.
  
• Customizable Output Folder and File Name — An administrator can define the name of an output document and output folder – for example, using a separator barcode value, or date and time indicators. It is also possible to define a particular destination and the file naming rules for each output format individually.
  
• Saving Recognition Results to FineReader Format — The results of the image analysis and recognition can be exported to internal FineReader format compatible with ABBYY FineReader Engine.
• Headers and Footers in Output PDF Files — Headers and footers can be added to output PDF and PDF/A files. Headers and footers may contain any static text, as well as page numbers, Bates numbers, the file name and the current date.
  
• Support for Custom Document Properties in PDF — When Recognition Server converts PDF files into searchable PDF, it retains all document properties fields that were present in the original PDF file. The administrator can also define new document properties for output PDF documents.
  

Functonality Overview

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

• Server Manager - the central service component, which controls the document processing queue and orchestrates the work of Processing Stations and Verification Stations.
  
• Processing Station - a service that performs recognition and document conversion.
  
• Verification Station - a client station which provides an interface for proofreading the recognition results.
  
• Remote Administration Console - a client console used for configuring and monitoring Recognition Server.

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

 1. Uploading documents

4. Getting Documents Converted

Administration

The administration of Recognition Server is performed via a convenient administration 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, and user permissions, to manage the processing queue and to view the log files.

The priority management and advanced scheduling features allow the administrator to control the order in which the documents are processed and use the stations’ hardware resources efficiently by scheduling OCR for night hours or weekends.

Integration

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.

Ideal Solution for High-volume OCR

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

In addition to its scalable architecture, ABBYY Recognition Server also offers a range of features aimed at making high-volume document conversion more productive yet cost-effective: 

• Document Convertion Automation — By eliminating user involvment in the conversion process ABBYY Recognition Server 2.0 significantly streamlines document processing workflow and reduces time spent on document input.

• Quick Deployment — Recognition Server is shipped as a ready-to-use solution which can be deployed in the corporate environment quickly and with minimal effort. In addition, it provides a rich set of tools to enable tighter integration with backend systems and scanning devices.

• Low-cost Administration — ABBYY Recognition Server 2.0 is a reliable solution designed to work in unattended mode and equipped with fault-tolerance functions. These features allow organizations to minimize management effort and reduce costs on system maintenance.

• Advanced Scheduling — The solution provides advanced scheduling options for managing task priorities and controlling the loading of processing stations during a day or week. For instance, some of workstations can be set up for round-the-clock operation, others – for night-time OCR processing, while at the day-time these workstations can be used to perform usual office tasks. These options save companies from purchasing additional hardware and allow using the existing resources in the most efficient way.

• Efficient Verification — ABBYY Recognition Server 2.0 includes client-side Verification Station designed for proofreading and correcting recognized texts. The program can be configured to apply verification to all recognized pages, to selected document types, or to pages with questionable quality only.

Recognition Server as Centralized OCR Service

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

For large organizations with hundreds or even thousands of employees which convert a variety of different document types, this per-user installation is no longer suitable to meet the needs of an entire company. The desktop installation in that case would require significantly more effort involved in maintenance, administration, training and supervision. In addition, the licensing cost of such a large-scale desktop installation may be unreasonably high.

The most efficient solution for large organizations doing distributed OCR processing is to deploy the single, centralized OCR and document conversion service running on a server backend. 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 network. All the company’s employees have got an access to the server-based OCR functionality automatically and all the time.

• Low-cost maintenance – The installation, configuration and administration of ABBYY Recognition Server are easy and time-efficient because these operations are performed from a single central point.

• No special training is required – ABBYY Recognition Server users don't need to have any knowledge about OCR technology at all. All they need to know about the program is where to send a document in order to get its recognized copy back.

• The single distributed system for all company’s offices – ABBYY Recognition Server supports remote access via e-mail and the Web and therefore can be accessible for users not only from within the local network but from remote computers as well (e.g. from users’ home PCs, from offices abroad or a partner office).

• Seamless integration with scanning devices and MFPs – Since Recognition Server runs centrally, an administrator can easily bind it with any scanning devices and MFPs in the company’s IT infrastructure so that all scanned documents can be automatically recognized and delivered back to the users in required editable or searchable formats.

Software Development and Integration

ABBYY Recognition Server provides a set of development tools allowing easy integration of the OCR functions into other server-based systems, such as enterprise content management (ECM), electronic records management (ERM) or document management systems (DMS):

COM-based API – An open COM-compatible Application Programming Interface (API) that allows third-party systems to transfer recognition tasks to ABBYY Recognition Server and retrieve output files.

Web service API – A programming interface that enables cross-platform integration and integration with remote systems and applications by using SOAP and HTTP protocols.

XML tickets – Program-generated XML files (XML tickets) used to customize processing parameters for certain documents. An XML ticket can be generated by means of ABBYY Recognition Server API or by a client application.

ABBYY Recognition Server offers the following benefits for software developers:

• Server-based architecture — Allows rapid integration of the OCR module with other server-based systems without spending extra time and resources on developing a Windows service functionality.

• Lower-cost integration with third-party systems and applications — Recognition Server’s high-level API provides access to the ready-to-use document conversion functionality that can be used without additional programming.

• The ability to easily scale the system and increase the OCR capacity by using additional hardware.

• High reliability and fault-tolerance of the OCR module — Ability to provide detailed information on the system operations, warning and error messages issued by the system.

• Document quality control — Ability to automatically sort out low-quality documents according to a pre-set accuracy threshold.

• SOA-ready solution — Recognition Server delivers ready-to-use Web Service interface and can be used as OCR Web Service in a service-oriented architecture.