Automatic invoice-data digestion based on 3rd party OCR SDK

The program that has to be developed in Visual Basic or C# is an Windows (XP/2000) desktop application that recognises data from invoices. The data recognised (supplier, products, total amount, etc.) should be saved as XML. Recognition of data has to be free so preferably no template definition. And when the data recognised is not 100% verified, manual checking is neccesary. The application should support multilingual interfaces (based on dictionary files). Default language is English (other languages are not part of project). OCR recognition functions are allready within a OCR SDK. This SDK ( [login to view URL]) has been used for these kind off programs before. If you have suggestions for other SDK's. I'm not fixed on the scansoft SDK. Feature summary: -Automatic Identification -Learns new documents automatically -Requires no invoice specific setup -Able to distinguish slight format variations -Works without logos or recognition -Map to vendor details, such as address -Rates match with confidence index -Rules-based Field Finding -Runs global rules on all invoices -Allows optional vendor-specific rules -Finds keywords with fuzzy matching -Finds fields by syntax, e.g. #PROD -Can use existing vendor list ## Deliverables 1) Complete and fully-functional working program(s) in executable form as well as complete source code of all work done. 2) Installation package that will install the software (in ready-to-run condition) on the platform(s) specified in this bid request. 3) Exclusive and complete copyrights to all work purchased. (No GPL, GNU, 3rd party components, etc. unless all copyright ramifications are explained AND AGREED TO by the buyer on the site per the coder's Seller Legal Agreement). ## Platform Windows XP pro and Windows 2000 pro