基于多尺度下LBP和PSO的织物瑕疵检测方法研究  

Defect detection method for silk based on LBP and PSO under pyramids decomposition

作　　者：李涛[1] 陈建英[1] 刘莉[1] LI Tao;CHEN Jian-ying;LIU Li(School of Computer Science and Technology,Southwest Minzu University,Chengdu 610041,P.R.C.)

机构地区：[1]西南民族大学计算机科学与技术学院,四川成都610041

出　　处：《西南民族大学学报（自然科学版）》2019年第1期66-71,共6页Journal of Southwest Minzu University(Natural Science Edition)

基　　金：四川省科技厅科技支撑项目(2013JY0041);四川省应用基础研究计划项目(2013JY0188);西南民族大学中央高校基本科研业务费专项基金(11NZYQN29)

摘　　要：针对丝织品疵点纹理与正常情况下织物纹理特征的不同,提出一种多尺度下LBP和PSO结合的织物疵点检测算法.首先对织物图像进行非线性的金字塔多尺度分解,再对各尺度图像提取对光照和旋转具有不变性的LBP特征,在此基础上,利用PSO的快速收敛特点计算各分块的LBP直方图的差异确定出疵点位置.实验结果表明,提出的方法具有较好的鲁棒性.In view of the texture’s difference between normal and defection parts of the silk,a novel defect detection method based on uniform LBP( Local Binary Pattern) and PSO( Particle Swarm Optimization) algorithm under pyramids decomposition was proposed. Firstly,the pyramids decomposition was implemented on the image,and then the uniform LBP algorithm was used to extract the texture feature on each level. Afterwards,PSO algorithm was applied to each fragment of sub-image to search the defection area. Experimental results showed that the proposed method has satisfactory detection precision.

关 键 词：金字塔分解 多尺度 局部二进制模式 微粒群算法 疵点检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]