Text Extraction and Recognition from Images

Abstract: Text recognition in images is an active field of research that aims to create a computer program with the ability to interpret text from images automatically. There is a huge demand nowadays to store the knowledge available on paper records in a machine-readable form for subsequent use. One convenient way to store data in the computer system from these paper documents is to first scan the documents and then store them as images. It is, however very difficult to read the individual material and scan the contents of these documents line by- line and word-by-word to reuse this information.

Keywords: Text extraction, summarization, Voice over, OCR