Steel Strip Defect Detection Based on Human Visual Attention Mechanism Model

Abstract:

According to the characteristics of steel strip, This paper propose the strip defect detection algorithm which is based on visual attention mechanism. First, extract the input image color, brightness and orientation characteristics and form simple feature map; secondly, prognosis on the features, get defective attention region by threshold segmentation to color characteristics of colored defect image. The wavelet decomposition to colorless defect image of brightness and direction features will form the multi-feature subgraph; then construct feature difference molecular graph through the feature decomposition map around central difference operations, and the characteristic difference of molecular graph is formed by the fusion of feature saliency map; finally, defect targets by using local threshold method and region growing segmentation. The experimental results show that this method can rapidly and accurately detect the defects of the strip image, at the same time it can improve the efficiency of detection.

• Periodical: Applied Mechanics and Materials (Volumes 530-531)
• Pages: 456-462
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.530-531.456
• Online since: February 2014
• Authors: Shuai Hua Xu*, Sheng Qi Guan, Long Long Chen
• Keywords: Center-Surround Difference, Srip Defect, Visual Attention Model

References

[1] Peng Zhang. Study on the mechanism of selective attention in image information processing. Changsha: The national defense science and Technology University, 2004. In Chinese.

[2] Xuewu Zhang, Xinnan Fan. Intelligent visual detection technology and calculation. Beijing: University of Electronic Science and Technology Press, 2013 . In Chinese.

[3] Itti L, Koch C. Nature Reviews Neurosdence, 2001, 2(3): 194-203.

[4] Wei Li, Xinhan Huang, Min Wang, Guohong Wang. Journal of Huazhong University(Natural Science Edition), 2003. In Chinese.

[5] Hong Wang , Desheng Zhu, WeiTang . Journal of Northeastern University(Natural Science), 2008, In Chinese.

[6] Jiahui Cong, Yunhui Yan. Chinese Journal of Mechanical Engineering, 2011, In Chinese.

[7] Shengqi Guan, Hongyu Shi, Yanni Wang. Journal of Iron and steel research, 2013, In Chinese.

[8] Yulan Wei, Bing Li, Dan Zhang. Advanced Materials Research, (2012).

[9] Xiansheng Qin, Feng He, Qiong Liu. Online defect inspection algorithm of bamboo strip based on computer vision[A]. Proceedings of the IEEE International Conference on Industrial Technology[C]. IEEE Computer Society Press, (2009).

DOI: 10.1109/icit.2009.4939598

[10] Francisco,G. B, Danhiel,F. G, Julio M. IEEE Industry Applications Magazine, (2013).

[11] JiaHui Cong, YunHui Yan, DeWei Dong. Dongbei Daxue Xuebao, (2010).

[12] Itti L，Koch C，Niebur E. IEEE Trans．Pattem Analysis and Machine Intelligence, (1998).