花色织物色彩识别的Bayes统计法  

Bayes Statistical Recognition of Fabric Colors

作　　者：张方强[1] 

机构地区：[1]浙江大学

出　　处：《纺织学报》2000年第3期34-37,44,共5页Journal of Textile Research

摘　　要：本文介绍一种用于花色织物ＣＡＤ／ＣＡＭ技术中色彩识别的自训练样本Ｂａｙｅｓ统计法。由于采用了新颖的开窗口取样本法、独特的样本分类及自训练方法，结果在无须任何先验信息的情况下，这种自训练样本Ｂａｙｅｓ统计法既极大地提高了彩色图象的识别精度、又拓宽了Ｂａｙｅｓ统计法的应用面。This paper introduces a sophisticated image color recognition method in color fabrics CAD/CAM technology. A decomposition method is designed to obtain color samples from the windows on the two-dimensional plane of a source image according to the distribution of the source image color clusters,and to train or classify these color samples step by step without any prior information. Application results show that the method can not only improve the quality of image color recognition,but also is of great value for the practical use in image recognition and many other fields.

关 键 词：Bayes统计法 花色织物 色彩识别 CAD/CAM 

分 类 号：TS105.11[轻工技术与工程—纺织工程] TP391.7[轻工技术与工程—纺织科学与工程]