Contents I. Introduction
After the advent of digital computers, incorporating human functions to computers has been an interesting and exciting research field [1]. For over years, humans have been thinking of machines with the ability to “read” and interpret printed textual documents, so that they can be automatically converted into an alternate medium or format [2]. Efficient algorithms have been developed so far so as to enable the machines to recognize characters. Such a system is named as Optical Character Recognition (OCR). This is a system developed for deriving character-based files from digitized images of printed or typewritten documents and/or handwritten manuscripts. Digitizing is done by using flat bed scanners or digital cameras. It is thus a process of visual recognition, which converts text documents into editable/searchable text.
