Classification of Incoming Documents

Does your organisation receive many documents, such as letters, forms and orders? If so, you are likely to store them electronically. Of course, you want to do that in such a way that you can easily retrieve and process these documents. That requires classification. Document Dialog offers you various solutions.

OCR for printed documents

The traditional classification method uses OCR. OCR is short for Optical Character Recognition. If you have scanned your documents, then OCR recognises the printed text. Your system then saves this text in one of the categories you have defined previously. This way, you can save your documents in a category based on customer number, insurance type or account number. OCR also makes sure that the text is saved in a file format that allows you to edit the file manually or automatically.

ICR for hand-written forms

If you receive documents that have been completed by hand (with a pen), ICR is the right solution. ICR stands for Intelligent Character Recognition and is used for interpreting hand-written texts. ICR has the same possibilities as OCR: it saves the text from your documents in the right manner and converts it to editable files. Moreover, a text that has been edited with ICR or OCR only needs a few kilobytes of storage space.

Self-teaching classification solutions

Many classification solutions use predefined templates. The system compares the scanned documents with the templates and recognises the characters that match. Self-teaching solutions do not need these templates. They compare the documents with a representative set of examples. If new examples are added or if the administrator makes corrections, they use these to learn from them as well.

If you like to know more about this, please make an appointment for a conversation. We are pleased to pay you a visit.