纺织学报 ›› 2014, Vol. 35 ›› Issue (6): 56-0.

• 纺织工程 • 上一篇    下一篇

几种基于图像自适应阈值分割的织物疵点检测方法比较

杜磊1 李立轻1,2 汪军1,2 万贤福1,2 陈霞1,2 李冠志1,2   

    1. 东华大学纺织学院
    2. 东华大学纺织面料技术教育部重点实验室
  • 收稿日期:2013-07-19 修回日期:2014-02-19 出版日期:2014-06-15 发布日期:2014-06-09
  • 基金资助:

    国家自然科学基金资助项目;中央高校基本科研业务费专项资金资助项目

 Comparison of several fabric defect detection methods based on image self-adaptive threshold segmentation

  • Received:2013-07-19 Revised:2014-02-19 Online:2014-06-15 Published:2014-06-09

摘要: 为了比较四种自适应阈值算法对目标和背景灰度值差异较大的织物疵点的检测效果,进而综合比较四种算法的优劣情况,本文首先对Otsu算法、改进的Otsu算法、局部阈值分割算法以及最大熵阈值法共四种图像自适应阈值算法的原理进行了介绍,然后分析了运用图像自适应阈值算法检测织物疵点的方法与步骤,在此基础上分别用四种自适应阈值算法对平纹和斜纹织物疵点图像进行了检测,并对检测结果进行了详细的分析和比较。实验结果证明文中所述四种自适应阈值算法在一定程度上都能用于织物疵点的检测,当不考虑算法执行时间时,检测效果为:局部阈值分割算法>改进的Otsu算法>Otsu算法>最大熵阈值法。当考虑算法执行时间时,综合检测效果为:局部阈值分割算法>Otsu算法>最大熵阈值法>改进的Otsu算法。

关键词: 自适应阈值分割, Otsu, 改进的Otsu, 最大熵, 局部阈值分割

Abstract: Four self-adaptive threshod algorithms were employed, respectively, to detect defects on plain and twill fabrics based on images and the results of the detection are analyzed, so as to compare the detection effcet of the four adaptive threshold algorithms in detecting defects of the fabercs whose gray values have a big difference from the background and then to find out their advantages and disadvantages. The experiment resultshows that all the four algorithms can be successfully used in fabric defectdetection. The order of the detecting effcet is: local threshold segmentation> improved Otsu> Otsu> maximum entropy when the time consuming is not considered. However, when the time consuming is considered the order is: local threshold segmentation> Otsu> maximum entropy> improved Otrsu.

Key words: self-adaptive threshold segmentation, Otsu, improved Otsu, maximum entropy, local threshold segmentation

[1] 李敏 崔树芹 陈佳. 应用视觉显著性的小提花织物疵点检测[J]. 纺织学报, 2016, 37(12): 38-42.
[2] 姬建正 刘建立 高卫东 潘如如 刘基宏 . 基于数字图像处理的纱线细度测量[J]. 纺织学报, 2011, 32(10): 42-0.
[3] 周志宇;刘喜昂;杨东鹤. 机器视觉在蚕茧表面积测量中的应用[J]. 纺织学报, 2006, 27(12): 29-31.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!