Image Fusion Method for Strip Steel Surface Detect Based on Bandelet-PCNN

Abstract:

To solve the problem of the pseudo-Gibbs phenomena around singularities when we implement image fusion with images of strip surface detects obtained from different angles, a novel image fusion method based on Bandelet-PCNN(Pulse coupled neural networks) is proposed. Low-pass sub-band coefficient of source image by Bandelet is inputted into PCNN. And the coefficient is selected by ignition frequency by the neuron iteration. At last the fused image can be got through inverse Bandelet using the coefficient and Geometric flow parameters. Experimental results demonstrate that for the scrip surface detects of scratches, abrasions and pit, fused image effectively combines defect information of multiple image sources. Contrast to the classical wavelet transform and Bandelet transform the method reserves more detailed and comprehensive detect information. Consequently the method proposed in this paper is more effective.

• Periodical: Advanced Materials Research (Volumes 546-547)
• Pages: 806-810
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.546-547.806
• Online since: July 2012
• Authors: Xu Zhang, Yun Hui Yan, Wen Hui Chen, Jun Jun Chen
• Keywords: Bandelet-PCNN, Image Fusion, Pseudo-Gibbs Phenomena

References

[1] Carisetti C A, Fong T Y, Fromm C. ILearn self-learning defect classifier [J]. Iron and Steel Engineer, 1998, 75(8): 50-53.

[2] Bilstein W, Enderle W, Moreas G, etal. Two systems for online oil film and surface roughness measurement for strip steel production [J]. Revue de Metallurgie, 2007, 104(7/8): 347-353.

DOI: 10.1051/metal:2007111

[3] Wang Yonghui, Yan Yunhui, Wu Yanping, Liang Huisheng. Image Fusion Based on Wavelet Transform for Strip Steel Surface Defects [J]. Journal of Northeastern University: Natural Science, 2009, 30(5): 728-732.

[4] Yan Yunhui, Song Kechen, Peng Yishu, Li Jun. On the Image Fusion Rules of Strip Surface Defects Based On Dissimilarity Between Local Variance [J]. Journal of Northeastern University: Natural Science, 2011, 32(1): 121-124.

[5] CANDESE J. Monoscale ridgelets for the representation of images with edges [R]. California: Stan ford University, (1999).

[6] CANDESE J. Ridgelets: Theory and applications [D]. Caifornia: Stanford University, (1998).

[7] CANDESE J, DONOHODL. Cuvelets [R]. California: Stanford University, (1999).

[8] DOMN, VETTERLIM. The contourlet transform: An efficient directionalmulti resolution image represe tation [ J]. IEEE Transactions on Image Processing, 2005, 14(12 ): 2091 - 2106.

DOI: 10.1109/tip.2005.859376

[9] Tao Guanqun, Li Dapeng, Lu Guanghua. On Image Fusion Based on Different Fusion Rules of Wavelet Transform. Acta Photonica Sinica, 2004, 33(2): 221-224.

[10] Zhang Qiang, Jing Zhongliang. Multi-focus image fusion using pulse coupled neural work [J]. Pattern Recongintion Letters, 2007, 28(9): 1123-1132.

DOI: 10.1016/j.patrec.2007.01.013

[11] Eckhorn R, Reitboek H J, Arndt M, Dicke P. Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex. Neural Computation, 1990, 2(3): 293-307.

DOI: 10.1162/neco.1990.2.3.293