基于改进自适应小波基的织物疵点检测算法  

FABRIC DEFECT DETECTION ALGORITHM BASED ON IMPROVED ADAPTIVE WAVELET BASIS

作　　者：刘洲峰[1] 李阳[1] 李春雷[1] 

机构地区：[1]中原工学院电子信息学院,河南郑州450007

出　　处：《计算机应用与软件》2016年第11期144-147,共4页Computer Applications and Software

基　　金：国家自然科学基金项目(61379113);河南省基础与前沿技术研究项目(142300410042);郑州市科技领军人才项目(131PLJRC643)

摘　　要：为了改进基于自适应小波的织物疵点检测效果,提出一种基于改进自适应小波基的织物疵点检测算法。首先通过不同限定条件优化得到多个自适应小波基;然后分别对疵点图像进行小波分解,采用最大类间方差法分割子图像;最后将多种自适应小波基分割后的图像进行融合得到检测结果。实验结果证明,该算法能够在较好保留疵点信息的同时,有效地减少检测结果中的噪声点。In order to improve the effect of adaptive wavelet-based fabric defects detection,we proposed a fabric defect detection algorithm which is based on the improved adaptive wavelet basis. First,the algorithm obtains a number of self-adaptive wavelet basis by optimisation with different limited conditions; then these self-adaptive wavelets are used to make wavelet decomposition on defect images respectively,and the Otsu method is used to segment the sub-image; finally,it fuses the images segmented by multiple adaptive wavelet basis to get the detection result. Experimental results demonstrate that the proposed algorithm can effectively reduce the noise points in test result while well preserving the defect information.

关 键 词：自适应小波 小波分解 图像融合 疵点检测 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]