基于小波包变换的模糊判决纹理分类  

Texture Classification by Completed Wavelet Packet Transform and Fuzzy Decision

作　　者：王晓丹[1] 靳华[1] 赵荣椿[1] 吴崇明[2] 

机构地区：[1]西北工业大学计算机科学与工程系,西安710072 [2]空军工程大学导弹学院计算机工程系,陕西三原713800

出　　处：《数据采集与处理》2001年第1期37-41,共5页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金;国家教委开放实验室基金资助项目

摘　　要：提出一种基于小波包变换的模糊判决纹理分类方法。采用图像的完全树结构小波变换提取多分辨率纹理特征 ,模糊判决分类器通过引入隶属度函数对特征模糊化 ,反映了各类纹理样本间存在的差异及随机噪声等畸变因素造成的抽取特征值存在的不确定性 ,提高了纹理分类算法对噪声或畸变的鲁棒性。A new texture classification approach by completed wavelet packet transform and fuzzy decision is proposed. The multi-resolution character of the texture is extracted by completed wavelet packet transform. By introducing membership function of the feature, the fuzzy decision classifier can make decision by the membership. The introduced membership function reflects the uncertainty of the feature values made by the difference between samples made by random noise. The proposed approach increases the robustness to noise. Simulational experiment gives a satisfactory result.

关 键 词：纹理分类 小波包变换 模糊判决 图像处理 计算机 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]