Structural and Statistical Feature Extraction Methods for Character and Digit Recognition

Abstract

Character recognition is the process of converting an image or PDF file into editable and searchable text file. Feature Extraction is the heart of any character recognition system. In the proposed paper, structural and statistical features of isolated English capital characters and digits are presented. New features like end point existence is zone and zone with zero foreground pixel value are presented in this paper. Features like zoning, number of endpoints, end point existence in zone, zone with zero foreground pixel value, number of horizontal line and number of vertical line are extracted from character. General Terms Character Recognition, Structural Features, Statistical Features