An Artificial Neural Network based Multistage Offline Handwritten Character Recognition

Devanagari is one of the basic Script widely used for many Indian Languages Like Hindi, Marathi, Rajasthani etc. Devanagari Scripts Hindi language is the third common language used all over the word. In this work we propose an artificial neural network based classifier and statistical and structural method based feature extraction. Optical isolated Hindi Characters are taken as an input image through the scanner. An input image is preprocessed and is segmented in terms of various structural and stastical features like End points, middle bar, loop, end bar, aspect ratio. Features are extracted and the feature vector is applied to Self organizing map (SOM) which is one of the classifier of an artificial neural Network. SOM is trained for such 500 different characters collected from 500 persons. The characters are classified into three different classes. The proposed classifier attains 91% accuracy.