中国机械工程 ›› 2011, Vol. 22 ›› Issue (10): 1189-1192,1221.

• 信息技术 • 上一篇    下一篇

视觉注意机制在带钢表面缺陷检测中的应用

丛家慧;颜云辉
  

  1. 东北大学,沈阳,110004
  • 出版日期:2011-05-25 发布日期:2011-05-31
  • 基金资助:
    国家高技术研究发展计划(863计划)资助项目(2008AA04Z135);国家自然科学基金资助项目(50574019) 
    National High-tech R&D Program of China (863 Program) (No. 2008AA04Z135);
    National Natural Science Foundation of China(No. 50574019)

Application of Human Visual Attention Mechanism in Surface Defect Inspection of Steel Strip

Cong Jiahui;Yan Yunhui
  

  1. Northeastern University,Shenyang,110004
  • Online:2011-05-25 Published:2011-05-31
  • Supported by:
     
    National High-tech R&D Program of China (863 Program) (No. 2008AA04Z135);
    National Natural Science Foundation of China(No. 50574019)

摘要:

针对图像中存在的低对比度及微小缺陷,提出一种基于人类视觉注意机制的带钢表面缺陷检测方法。该方法以人类视觉系统的生理结构和功能为基础,结合Gabor滤波器多尺度、多分辨率的特点和人类视觉系统所具有的多通道和多分辨率特征,建立了带钢表面缺陷检测模型。实验结果表明,该方法不但可准确检测出缺陷区域,得到区域焦点位置坐标,而且检测速度快,可以满足在线实时检测要求。

关键词:

Abstract:

It is difficult to judge the defects if only based on gray information. In response to the low contrast and small defects, a novel algorithm based on human visual attention mechanism was proposed. According to biological structure and function of human visual system, a detection model was built combining multiple scales and frequencies of Gabor filter with multichannel and multifreqency of human visual system.
The experimental results show that this method is effective to detect the surface defects and establish the coordinate position of defect region. The inspection speed is fast,which can satisfy the real-time detection system’s demands. 

Key words: human visual system, attention mechanism, surface defect inspection, Gabor filter

中图分类号: