An Efficient Feature Extraction Method for Handwritten Character Recognition

Abstract

Handwritten character recognition in a particular language is one of the favourite topics for research from two last decades. Image processing and pattern recognition plays a lead role in handwritten character recognition. It is not a easy task to build a program to achieve hundred percent accuracy for handwritten characters because even humans too make mistakes to recognize characters. There are three main steps of handwritten character recognition- Data collection and preprocessing, feature extraction and classification. Data collection includes creating a raw file of handwritten character images. Preprocessing steps are applied to find a normalized binary image of handwritten character which is easy to process in next step. Feature extraction is the process of gathering data of different samples so that on the basis of this data we can classify samples with different features. Feature extraction from preprocessed handwritten character plays the most important role in character recognition. Thus feature extraction stage in handwritten character recognition system has a large scope for researchers. In this paper, we also introduce a new feature extraction method for handwritten characters named Cross-corner. We use the results of some promising feature extraction methods to find the best method for this application.