DocuShare OCR Alternatives
Xerox DocuShare OCR Module - this sells for $4000 and generally is sold with Content Rules for $7500. The OCR Module can be used by itself, but it is a manual process where you'd select documents one at a time using the blue triangle to the right and tell it to convert to a format of your choice (Word, Excel, PDF, text). Content Rules allow you to set a rule that is triggered when you add images to a collection (and subcollections) to convert to a specific format. That's good for batch conversions of incoming documents. You can also have DocuShare convert pre-existing documents by adding Lifecycle Manager for $5000 and telling it to convert specific collections of documents on a given date. If you had a half million images to convert, you could use the OCR Module + Content Rules + Lifecycle Manager to convert your files by collection and/or date so they don't all trigger at once. OCR processing takes a lot of CPU power and the notion of running this on your DocuShare server for large numbers of documents is rather unwise, but it can be done. One good thing about the OCR Module is there is no page count limit.
http://www.avidoffice.com/docushare/dsweb/View/Collection-713
An alternative to that If you have a lot of image files already in DocuShare then you can consider our DocuShare OCR Crawler to monitor your collection trees to convert those to searchable PDFs using either ABBYY Recognition Server or ABBYY FineReader based on your volume of documents. We have this bundled with various configurations for you or we can look for a more perfect fit. This is generally less expensive than the Xerox DocuShare OCR Module.
http://www.criteriafirstware.com/Criteria-First-Products/DocuShare-OCR-Crawler-p386.html
ABBYY Recognition Server - this starts at $1850 for 100K PPY (Pages Per Year) and can be used for many purposes including scanning or copying files into a watched folder to output to your preferred format (Word, Excel, PDF, ePub, text, etc.) and you direct the output to another folder. It also comes with one Scanning station which allows you to split or combine documents, one Verification station for error correction, and one Indexing station for tagging documents with exported CSV or tab-delimited files. The indexing station lets you fill in fields by clicking on words and numbers or highlighting lines and phrases to export.
ABBYY Recognition Server allows you to create up to 32 unique workflows for incoming fax, email, ftp, shared folder (SMB), and web submissions for all kinds of OCR conversion operations around the office. Accuracy is understood to be much better than the DocuShare OCR Module. If you need more than 100K PPY, give me an estimate of your volume and I'll provide you with a quote.http://www.criteriafirstware.com/ABBYY-Recognition-Products/ABBYY-Recognition-Server-4-p197.html
When used with our DAVupDoc auto-filer for $1495 you can upload the exported files into DocuShare with new titles and searchable metadata with your fully searchable documents. DocuShare's included Content Intake Module ($0) will upload files very fast (tested on up to 1 million documents per day) where the indexing occurs immediately afterwards so users can start searching.
http://www.criteriafirstware.com/Criteria-First-Products/DAVupDoc-p9.html
ABBYY FlexiCapture extracts data from images derived from email attachments, scans, and other image formats and exports PDFs (typically) with data for databases, spreadsheets, and CSV files that can be used with DAVupDoc for autofiling. Custom export formats can be created for use with various systems. FlexiCapture works with both structured (forms and surveys) and unstructured (invoices, orders, EOBs, remittances, contracts, etc.) documents and comes in Standalone or Distributed multi-users configurations.