自适应局部二值模式算法及其在织物疵点检测中的应用  

Adaptive local binary patterns and its application in fabric defect detection

作　　者：付蓉[1,2] 石美红[1] 陈惠娟[1] 

机构地区：[1]西安工程大学计算机科学学院,陕西西安710048 [2]西安电子科技大学影像处理系统国家重点实验室,陕西西安710071

出　　处：《纺织高校基础科学学报》2010年第1期99-104,共6页Basic Sciences Journal of Textile Universities

基　　金：陕西省科技厅13115科技创新工程(2008ZDKG-36);陕西省教育科技项目(05JC13)

摘　　要：为了能够准确地提取不同纹理的特征,提出一种新的纹理特征提取方法,自适应局部二值模式为不同纹理特征创建相应的主要概率模式子集,避免了均匀局部二值模式使用同一模式集描述不同纹理结构而导致的描述不准确问题.在该算法基础上构建一种新颖的织物疵点检测算法,使用本文提出的特征提取方法获取无疵点织物图像特征并确定疵点判断阈值,然后将待检测织物图像分割为大小相同的检测窗提取特征后,与阈值比较以判断是否为疵点区域.实验证明此算法不仅保持了传统LBP的旋转不变、多分辨率等特点,而且疵点检测结果在视觉上更加细腻、误检率更低、适用范围更广.An advanced local binary patterns method is proposed to precisely describe image features. Adaptive local binary patterns （ALBP） method selects the frequently occurred patterns to construct the main pattern set, which avoids using the same pattern set to depict different texture structures in traditional uniform local binary patterns. Based on the proposed method an effective fabric defect detection algorithm is designed. First the features of free defect image are extracted according to the main pattern set and the threshold is confirmed. Then the image to be tested is divided into same size detection windows from which ALBP features are also extracted. The features are compared with the threshold to find the defective window. The experiments exhibit the detection effect of the proposed method is comparatively better than traditional LBP from visual aspect and detection accuracy.

关 键 词：局部二值模式 图像分割 疵点检测 特征选择 工业检验 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]