ABSTRACT
The traditional way of working in any organization or department involved a lot of paperwork where documents were typed, printed, and circulated. The forms were manually filled and processed. Then the automated systems came and took on the bulk of the job. Even though automation has covered most fields, paper still continues to survive and intermingles with the automated counterparts at various fronts. This necessitates and motivates the use of systems that can automatically read and extract characters from any picture, scanned document, web-acquired image with text, etc. Character recognition is a field that deals with the recognition of characters embedded in pictures that may be acquired in numerous ways, depending upon the system under study. Optical character recognition (OCR) applies to the printed documents that have optical characters placed on them. A related field is handwriting recognition, where we try to extract text scribbled by a person.
