Development of Novel Techniques to Recognize Tamil Language Characters

Abstract

Despite the widespread utilization of PCs in record preparing, hand-printed archives assume a significant job in our life. The machine investigation of hand-printed records has extraordinary hugeness in this period of paperless workplaces. The machine investigation of records arranged with paper and pen is alluded to as disconnected handwritten archive recognition frameworks. Character recognition is a key, however generally testing in the field of example recognition with a huge number of valuable applications. In this paper proposed to Fuzzy Neural Network utilizing Tamil script language recognition framework, a successful dynamic shape with MRF and Fuzzy Neural Network with Fuzzy C Means is used for character recognition and proficient district-based dynamic form with Improved Markov Random Field (IMRF) and support-vector-based fuzzy neural network classification (SVFNNC) system are recommended to improve the recognition exactness. The exhibition of the proposed plan is assessed utilizing different measurements, for example, Accuracy, Precision, Recall, and F-measure.