• CN：11-2187/TH
  • ISSN：0577-6686
机械工程学报

›› 2013, Vol. 49 ›› Issue (22): 34-40.

• 论文 • 上一篇    下一篇

扫码分享

隐马尔可夫树模型在带钢表面缺陷在线检测中的应用

徐科;宋敏;杨朝霖;周鹏   

  1. 北京科技大学高效轧制国家工程研究中心
  • 发布日期:2013-11-20

Application of Hidden Markov Tree Model to On-line Detection of Surface Defects for Steel Strips

XU Ke;SONG Min;YANG Chaolin;ZHOU Peng   

  1. National Engineering Research Center for Advanced Rolling Technology, University of Science and Technology Beijing
  • Published:2013-11-20

PDF

352

摘要： 通过图像分割算法寻找由缺陷组成的可疑区域是热轧带钢表面缺陷在线检测与识别的关键。将热轧带钢表面图像分为“背景”和“缺陷”两大类，采用隐马尔可夫树(Hidden Markov tree，HMT)模型分别建模并实现多尺度缺陷分割。将不同类别的缺陷用同一个“缺陷模型”来表示，可以降低算法复杂度。HMT模型对带钢表面常见缺陷的分割正确率达到94.4%，分割错误率为18.8%。针对HMT模型得到的细尺度分割结果中分割错误率较高问题，引入基于环境的多尺度融合方法(Context-adaptive hidden Markov tree, CAHMT)，将不同尺度的分割结果融合，大幅降低细尺度分割的分割错误率，达到3.7%。

关键词: 表面检测, 热轧带钢, 图像分割, 隐马尔可夫树模型

Abstract: Finding suspicious areas with algorithms of image segmentation is essential to on-line detection and recognition of surface defects for hot-rolled steel strips. Surface images of steel strips are divided into two categories：“background” and “defect”, and the two categories are modeled by hidden Markov tree(HMT) respectively and are detected at different scales. Detecting various types of defects by a same “defect” model could greatly reduce the algorithm complexity. The detection rate of common steel strip defects by hidden Markov tree model is 94.4% and the false rate is 18.8%. To reduce the steel strip’s defects segmentation false rate at finer scales, the context-adaptive hidden Markov tree model(CAHMT) is introduced and used to fuse the raw segmentations of HMT model at different scales. By the help of CAHMT, the false rate reaches 3.7%.

Key words: Hidden Markov tree model, Hot-rolled steel strip, Image segmentation, Surface inspection

中图分类号: 

版权所有 © 2019 《机械工程学报》编辑部 | 京ICP备05055788号-30