Ankita Sikdar, Payal Roy, Somdeep Mukherjee, Moumita Das and Sreeparna Banerjee, West Bengal University of Technology, India

This paper gives complete guidelines for authors submitting papers. This paper aims to explore a new way for recognizing printed Bengali characters. Keeping in mind, the possible shapes and orientations of the Bengali characters, we have developed a method to classify each of the 50 Bengali characters. An exhaustive study of the features of Bengali characters has been carried out which is presented in a hierarchical structure. The first few layers deal with features that broadly classify the characters into small size groups. The lower level features are more specific to each character within a group. While the higher level features can be identified based on pixel density and arrangement, the lower level features have been identified using chain code technique. The computer has been programmed to progress successively through each group in the hierarchy until it finds a match with the input character or rejects it.

Bengali Character Feature Identifications, Chain Code Technique & Feature Extraction