Abstract: “Character segmentation is the critical area of the Optical Character Recognition process. The higher recognition rates for isolated characters as compared to those obtained for words and connected character strings illustrate this fact. This paper provides a review of various techniques of character segmentation, which are classified mainly into four classes. In classical approach the input image is partitioned into sub images, which are then classified.”

Keywords: segmentation, contextual method, graphemes, Hidden Markov Models, holistic recognition, Optical character recognition, recognition-based segmentation and survey