ABBYY Recognition Server
ABBYY Recognition Server – is a powerful server-based software solution for automating document processing, received by fax or MFD and PDF conversion in document management and storing systems. ABBYY Recognition Server automatically converts documents into fully searchable and viewable formats such as PDF, MS Word, HTML, etc.
Usage scenarios include
- Creation of Digital Archives
ABBYY Recognition Server provides fast conversion of paper documents into electronic form and further archiving. Scanning and recognition is completed automatically – all you have to do is to set the processing scenario.
- Document scanning in the “registry” mode
ABBYY Recognition Server solves the problem of saving paper documents in the corporate information system. Convenient interface of scanning and indexing station allows scanning and registering documents in the system within several clicks.
- Text recognition service for every office worker
All you need is to install one copy of ABBYY Recognition Server in your local network and the recognition service will be available to all company employees. Every worker will get the possibility to recognize any necessary document.
- Document recognition for corporate search systems
ABBYY Recognition Server is integrated with Google Search Appliance™, Microsoft® Office SharePoint® Server and with search server Windows® Search on the work stations. It enables the users to perform the full-text search for documents stored as images both in corporate network and PC.
ABBYY Recognition Server. How it works
Image capture
- Supported formats: PDF, BMP, PCX, PNG, DCX, JPEG, JPEG2000, TIFF, DjVu
- Scanning via TWAIN, WIA, ISIS interfaces. Several scanning stations can be operated in the corporate network
- Capturing images from local or network folder, including complex structural folders (with embedded subfolders). When saving the results in the file system the program recreates the structure of incoming folder
Setting Document Type and Attributes
- Image stream splitting into documents by blank pages, separating barcode, fixed number of pages or more complex rules defined by script
- Automated document type detection and attribute setting by script defined rules
- Document type detection and attribute setting manually at indexing station
Recognition
- Recognition of multilingual documents in more than 190 languages
- The fast recognition mode will result in much faster processing of good quality images
- Adaptive Document Recognition Technology (ADRT). It provides analysis of document as a whole unit and full logical structure of entire document retention: content, heading hierarchy, page numbers, headers, footers, and also font styles
- Recognition of text special types: MICR (E13B), OCR-A, OCR-B, Gothic types
- Supported recognition of the most popular 1D and 2D barcodes
- Recognition of attachments from letters sent by e-mail client or via network scanner or MFD
- Setting of a threshold for recognition accuracy based on allowance of indefinitely recognized characters per page
- Recognition accuracy control at verification station
Publishing
- Saving documents in the most popular formats: DOC, DOCX, XLS, XLSX, HTML, TXT, PDF, PDF/A, TIFF, JPEG, JPEG2000, CSV
- Naming documents in accordance with specified rules using barcodes, date, time, etc.
- Publishing documents to the network folder or Microsoft Office SharePoint Server libraries
- Sending documents via e-mail
- Delivering documents and attributes to the document management systems or storing them via script