Multi Resolution Feature Based Active Handwritten Character Recognition

Abstract

This paper is based on hierarchical classification technique for offline recognition of handwritten characters. Different feature extraction methods are designed for different representations of characters such as solid binary characters, character contours, skeletons or gray level images of each individual character. The problem of choosing the appropriate feature extraction method is related with a given application. Multi-Resolution features are used in this implementation. The traditional method follows the static model for recognition. This recognizer uses the dynamic and hierarchical classification method for character recognition.