International Journal of Artificial Intelligence and Neural Networks
Author(s) : JUHI KANERIA, KANDARP PANDYA, KRUTI J DANGARWALA, RUCHITA TAILOR, THAKKAR NIRAV B
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. The operation of attempting to decompose the image into classifiable units is called “dissection”. In the second class of method, the dissection method is avoided and the image is segmented either explicitly by classification of pre specified windows, or implicitly by classification of subsets of spatial features collected from the image.