Odia Offline Character Recognition

Abstract

Optical Character Recognition (OCR) is a document image analysis method where scanned digital image that contains either machine printed or handwritten script are input into a system to translate it into an editable machine readable digital text format. Development of OCRs for Indian script is an active area of research today. This is an attempt towards making an OCR system for the Odia script. Odia language present great challenges to an OCR designer due to the large number of letters in the alphabet, the sophisticated ways in which they combine and many characters being roundish and similar in looks. The Biju Patnaik Central Library at NIT Rourkela is making a lot of effort in preserving Odia books. But, the space requirement is huge which can be compressed by the use of an Odia OCR.

In this project, an attempt is made to recognize the Odia characters by the use of the Gradient Features of a character image. The features extracted are then classified with the help of an Artificial Neural Network. Further, a method of nesting of Artificial Neural Networks is proposed for greater accuracy of the recognition algorithm and a faster numeral recognition algorithm for Odia numerals by using parts of the character instead of the whole image.