Recognition of Offline Handwritten Hindi text using middle zone of the words

Offline Handwritten Hindi text recognition is very challenging task. A novel attempt is made by us to recognize handwritten Hindi text using segmentation based approach. Although many efforts have been made to recognize isolated characters and words, a little work has been done to recognize the offline handwritten Hindi text by segmenting the sentences into lines and lines into words. The uniqueness of this approach lies in the fact that many of the commonly used words can be recognized when all the characters in the middle are recognized even by ignoring the upper modifiers, lower modifiers and half characters. Another advantage is that it is not word specific i.e. any number of words can be added to the list to be recognized. Topological features are extracted in programming by applying many heuristics and efforts are made on the correctness of the features. Results obtained with the proposed technique are very challenging.