基于二次样条小波变换极大模的织物疵点检测方法  

Fabric Defect Detection Based on Quadratic Spline Wavelet Transform Modulus Maximum

作　　者：袁晔[1] 

机构地区：[1]北京服装学院工业设计与信息工程学院,北京100029

出　　处：《北京服装学院学报（自然科学版）》2007年第2期25-30,共6页Journal of Beijing Institute of Fashion Technology：Natural Science Edition

摘　　要：提出了一种基于二次样条小波变换极大模的织物疵点检测方法:首先由二次样条小波对织物图像进行分解,利用分解后的纬向和经向2个子图像建立正常织物图像和待检测织物图像的极大模边缘图像,并求得它们的差分图像;然后由差分图像提取特征参数检测织物疵点以及识别疵点的位置.实验表明:这种方法具有检测准确率高,稳定性好等优点.A method of fabric defect detection was presented based on quadratic spline wavelet transform modulus maximum theory. Firstly, a fabric image was decomposed by using the spline wavelet transform and forming two subimages that matched warp and weft texture respectively. Secondly, a local maximum modulus theory based on single-scale edge image was reconstructed from the warp and weft subimages. Further, from the difference image between two edge images, the features were extracted to detect the fabric defect and identify the fabric defect location. Experimental results showed that the algorithm was chiefly characterized by great accuracy and perfect robust.

关 键 词：样条小波 图像分解 织物疵点检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]