Hand Written Odia Character Recognition

Abstract

The world is fast moving towards digitalization. In the age of super-fast computational capabilities, everything has to be made digitalized so as to make the computer understand and thereby process the given information. Optical character recognition is a method by which the computer is made to learn, understand and interpret the languages used and written by the human beings. It provides us a whole new way by which computer can interact with human beings, in their own languages. Hence OCR has been a topic of interest for researchers all around the globe in the past decade and research paper involving OCR is increasing day by day. It is seen that efficient algorithms have increased the speed and accuracy of character recognition. A substantial amount of work has been done on foreign languages such as English , Chinese etc. but very few paper are there for Indian languages baring a few for Hindi and Bengali. Hence our research work was directed towards development of a novel algorithm for Odia character recognition.
Odia is one of the eighteen languages recognized by the Indian constituency. It is also one of the oldest languages and is spoken by more than 44 million people in the state of Odisha. Recognition of this particular language is difficult because of a number of similar looking characters and the presence of complex characters.
A novel technique is proposed and implemented for the feature extraction method where by a set of 81 feature vectors are extracted to uniquely identify a particular character. The recognition is based on finding the minimum error by implementing the Euclidean distance method. After the implementation of the above technique, accuracy was found to be about 70 % which is much better than many techniques earlier available.