Document Examiner
Document Examiner is an application that indexes and clusters documents based upon the content of the OCR and/or extracted text. Document Examiner not only will find potentially duplicate items, it will also find documents of similar type. We have found a potential of a 30% grouping ratio based upon internal test results. This application is currently free as we are requesting feedback from our customers regarding its output and features. All you have to do is point the client application to the parent directory of the text files and it will do the rest. It only indexes files with .txt extensions so if the OCR is with the images it will work just fine (OCR must be in multi-page format, if you need help converting single page OCR to multi-page OCR please contact us). Just send us the index file the application creates and we will process the data and return you a load file. Currently we only offer the load file in Summations ParentID, AttchIDs format but we would love to create a custom output for you. Just let us know how you would like the delivery and we will customize it to fit your needs. **No information is contained in the index file other than numeric values and the name of the text files**
Click Here to Proceed to Download
The Document Examiner is currently being re-written and new information will be posted here when it is available.