视觉注意机制在带钢表面缺陷检测中的应用

被引:13
作者
丛家慧
颜云辉
机构
[1] 东北大学
基金
国家高技术研究发展计划(863计划);
关键词
人类视觉系统; 注意机制; 表面缺陷检测; Gabor滤波器;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
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。
引用
收藏
页码:1189 / 1192+1221 +1221
页数:5
相关论文
共 10 条
[1]  
A selective ttention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. Salah A A,Alpaydin E,Akarun L. Pattern Analysis and Machine Intelligence, IEEE Transactions on . 2002
[2]  
The JPEG 2000 still image coding system: An overview. Charilaos Christopoulos,Athanassios Skodras,Touradj Ebrahimi. IEEE Transactions on Consumer Electronics . 2000
[3]  
Computational modeling of visual attention. Itti L,Koch C. Nature Reviews Neuroscience . 2001
[4]  
Perception and Communication. Broadbent,D. E. . 1958
[5]  
A model of saliency-based visual attention for rapid scene analysis. Itti L,Koch C,Niebur E. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1998
[6]  
Perception,Attention,and Re-sources:A Decision-Theoretic Approach to Graphics Rendering. Horvitz E,Lengyel J. Proceedings of the ThirteenthConference on Uncertainty in Artificial Intelligence . 1997
[7]  
Models of Bottom-up and Top-down Visu-al Attention. Itti L. . 2000
[8]  
SocialConstraints on Animate Vision. Breazeal C,Edsinger A,Fitzpatrick R,et al. IEEE IntelligentSystems . 2000
[9]  
Discrete Gabor transform. Qian S,Chen D. IEEE Transactions on Signal Processing . 1993
[10]  
A cortical model of winner-take-all competition via lateral inhibition. R. Coultrip,R. Granger,G. Lynch. Neural Networks . 1992