Document Scanner || A CODECLOUDS Community Initiative

OCR/ICR– These processes involve converting the text on document images to text that can recognized by a computer application. Optical and Intelligent Character Recognition uses computer algorithms to read the printed text on a document image and converts that text to ASCII, XML, or some other sort of electronically usable language. Once converted, the words can be used to index the document images or to feed other applications.

IDR - Over the past few years, a concept called intelligent document recognition (IDR) has been introduced and accepted into document imaging applications. IDR involves the automated capture of data from, and classification of, complex documents. It enables a user, for example, to automatically extract relevant data from invoice forms, which, although they contain similar information, can look vastly different.