Optimized and Efficient Feature Extraction Method for Devanagari Handwritten Character Recognition

Online handwritten character recognition is having wide areas of application in real life environment. Therefore the accuracy of such systems should be more, efficient and faster to process applications. A lots of research work is still going on over handwritten character recognition based on different languages and scripts. For any handwritten character recognition, there are three main tasks such as Image segmentation, Feature Extraction and Classification. Feature extraction is a very essential step for online handwritten character recognition. As the success rate of a recognition system is often depends on a good feature extraction method. The feature extractor determines which properties of the preprocessed data arc most significant and should be used in further stages. In this paper different feature extraction methods are discussed and presented related with Devnagari script and proposed efficient and optimized extraction method with their comparative analysis. The accuracy of recognition system is majorly depending on feature extraction phase, types of features and size of features. The hybrid efficient, faster and optimized feature vector is used which is combination of geometrical features, regional features, distance transform and gradient features. Feature vector length is 91. In addition to this, in existing cases, the time required for extracting the geometrical features is very high; however Universe of discourse is used to speed up the retrieval. From practical analysis, accuracy of proposed feature vector set is improved as compared to existing feature vectors.