STATISTICAL PATTERN-RECOGNITION USING EFFICIENT 2-DIMENSIONAL MOMENTS WITH APPLICATIONS TO CHARACTER-RECOGNITION

作     者：TSIRIKOLIAS, K MERTZIOS, BG 

作者机构：Automatic Control Systems Laboratory Department of Electrical Engineering Democritus University of Thrace 6 Author to whom all correspondence should be addressed. 

出 版 物：《PATTERN RECOGNITION》 (图形识别)

年 卷 期：1993年第26卷第6期

页      面：877-882页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：MOMENTS STATISTICAL PATTERN RECOGNITION CLASSIFICATION CLUSTERING STATISTICAL SIGNAL PROCESSING OCR 

摘      要：A new set of efficient two-dimensional (2D) moments is introduced, which are normalized with respect to standard deviation. They are invariant under rotation, translation and scale of the image, less sensitive to noise and appear to have better classification performance over the existing sets of moments. Application of the proposed technique to optical character recognition is given.