Recognition of Offline Handwritten Hindi Text Using SVM

Handwritten Hindi text recognition is emerging areas of research in the field of optical character recognition. In this paper, a segmentation based approach is used to recognize the text. The offline handwritten text is segmented into lines, lines into words and words into character for recognition. Shape features are extracted from the characters and fed into SVM classifier for recognition. The results obtained with the proposed feature set using SVM classifier is very challenging