期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2012
卷号：2
期号：5
出版社：S.S. Mishra
摘要：This paper presents feature extraction, feature selection and statistical classifier for pattern recognition. The binary image of a pattern is partitioned into regions for feature extraction to represent them. The set features are extracted by the density and vector distance one's in each region. The class discriminating power of each region feature is evaluated to select high quality feature. The statistical classifier is developed from the interclass region features. The performance of the classifier is tested on handwritten numeral database and found good classification / recognition rate
关键词：Feature extraction and selection; statistical classifier; character recognition; Knowledge base
