方向性纹理织物疵点检测方法研究  

A Detection Method of Directional Texture Fabric Defects

作　　者：管声启[1] 

机构地区：[1]西安工程大学机电工程学院,陕西西安710048

出　　处：《计算机工程与科学》2011年第3期73-76,共4页Computer Engineering & Science

基　　金：西安工程大学博士科研基金项目(BS1005)

摘　　要：通过分析方向性织物纹理的特点,提出了一种织物疵点检测新的方法。首先根据正常纹理Hough变换确定织物纹理的纹路方向;然后采用方向性小波对织物纹理图像进行方向性的分解,并在此基础上从分解后的各细节子图中提取子窗口的特征;最后通过BP神经网络进行织物疵点识别。实验结果表明了该方法的有效性。By analyzing the characteristics of directional fabric textures, a new method for defect detection is presented. Firstly, the main lines of texture fabric texture are detected by the normal fabric texture Hough transform. Then, fabric texture images are decomposed by the directional wavelet. On this basis, the sub-windows of characteristics are extracted from the detailed sub-images. Finally, the fabric defects are identified by the BP neural network. The experimental results show that this method is effective.

关 键 词：方向性纹理 HOUGH变换 小波分解 疵点检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]