期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：64
期号：1
出版社：Journal of Theoretical and Applied
摘要：The recognition of handwritten characters and numerals has been a challenging problem among the researchers for few decades. This paper proposes a relative density feature extraction algorithm for recognizing unconstrained single connected handwritten numerals independent of the languages. The proposed method consists of four phases, namely, image enhancement (dilation), representation (zone based), feature extraction (relative density) and recognition (minimum distance classifier). The handwritten numerals must be enhanced with dilation, in order to connect the broken digits. After enhancement, the dilated binary images can be represented as a mid-point aspect ratio class interval values. There can be M * N zones and subsequently there would be 2M*N relational density exist using mid-point aspect ratio class interval values. In order to minimize the number of features, a subset of W relative densities has been extracted from the binary image since the relative density is too large to be handled efficiently. The minimum distance classifier technique has been used to recognize the given numerals. The proposed algorithm would be an alternative to recognize the handwritten numerals for recognizing unconstrained single connected handwritten numerals. The method sounds promising with a recognition rate of 92.8567%.
