HCR Using K-Means Clustering Algorithm

Hindi is a national language of India, there are about 300 million people in India who speak Hindi and write Devnagari script. A problem of Hindi character recognition is addressed and I propose a recognition mechanism based on k- means clustering. The large dataset of Hindi characters and their similarity makes the problem as there is no separation between the characters of texts written in Hindi as there is in English. K-means provides a natural degree of font independence and this is to reduce the size of the training database. In this paper I propose an OCR for Hindi characters, using K-means clustering. The major steps which are followed by a general OCR are preprocessing, character segmentation, feature extraction, classification and recognition. The paper introduce propose a two masks one is for horizontal projection and other for vertical projection of gray scale image to detect& eliminate shirorekha of word to decompose into individual characters from the words.