TEXTURE SEGMENTATION METHOD BY USING 2-DIMENSIONAL AR MODEL AND KULLBACK INFORMATION

作     者：OE, S 

作者机构：Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Minamijosanjima Tokushima-city Tokushima 770 Japan 

出 版 物：《PATTERN RECOGNITION》 (图形识别)

年 卷 期：1993年第26卷第2期

页      面：237-244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：PATTERN RECOGNITION TEXTURE SEGMENTATION TEXTURE RANDOM FIELD TEXTURE MEASURE 2-DIMENSIONAL AUTOREGRESSIVE MODEL KULLBACK INFORMATION DISCRIMINANT FUNCTION 

摘      要：This paper deals with a segmentation Method of texture image with randomness. For the texture segmentation, the statistical characteristics of texture are extracted by a texture measure, and it is necessary to discriminate textures by using the measure. In this paper new discriminant functions based on two-dimensional autoregressive models fitted to the texture image being considered and Kullback information which can measure the distance between two probability distributions are proposed. Furthermore, the texture segmentation method using this function is proposed. By numerical examples the validity of the method is verified.