In the foam nickel process, texture is the indicator of foam nickel performance. In order to recognize foam nickel surface defects accurately and provide guidance for production operations, this paper proposes a method for extracting foam nickel image textures based on multi-scale texture analysis. First, nonsubsampled contourlet (NSCT) is used to carry out foam nickel image multi-scale decomposition, and the low-frequency and high-frequency components following decomposition are used to characterize different defect details. Then, the Haralick eigenvalue, which measures the foam nickel image texture information at each sub-band, is calculated. The KPCA and optimal DAG-SVM are adopted in order to reduce the parameter dimension and clarify defects. Tests are carried out on the foam nickel surface image samples, including crack, scratch, pollution, leakage, and indentation tests. The results indicate that the method proposed in this paper can extract different pieces of detailed texture information and can achieve a defect-identifying accuracy of up to 88.9%.

1. [1] National Development and Reform Commission, Ministry of Science and Technology, Ministry of Industry and Information Technology, Ministry of Land and Resources, Ministry of Urban and Rural Construction, Department of Commerce, “China Resources Comprehensive Utilization Technology Policy Outline,” 2010.
2. [2] C. Dai, D. Wang, X. Hu, et al., “Production technology of continuous nickel foam,” The Chinese J. of Nonferrous Metals, Vol.13, No.1, pp. 1-14, 2003.
3. [3] Technical Committee of the National Standard for Nonferrous Metals, “GB/T20251-2006 Foam nickel for battery,” Standards Press of China, 2006 (in Chinese).
4. [4] R. S. Medeiros, J. Scharcanski, and A. Wong, “Image segmentation via multi-scale stochastic regional texture appearance models,” Computer Vision and Image Understanding, Vol.142, pp. 23-36, 2016.
5. [5] X. Xue and M. Xiao, “Application of genetic algorithm-based support vector machines for prediction of soil liquefaction,” Environmental Earth Sciences, Vol.75, No.10, pp. 1-11, 2016.
6. [6] H. Li, H. Qiu, Z. Yu, et al., “Infrared and visible image fusion scheme based on NSCT and low-level visual features,” Infrared Physics & Technology, Vol.76, pp. 174-184, 2016.
7. [7] D. Wang, S. Gan, W. Zhang, and W. Lei, “Strip Surface Defect Image Classiflcation Based on Double-limited and Supervised-connect Isomap Algorithm,” Acta Automatica Sinica, Vol.40, Issue 5, pp. 883-891, 2014.
8. [8] Y. Yang, Z. J. Zha, M. Gao, et al., “A robust vision inspection system for detecting surface defects of film capacitors,” Signal Processing, Vol.124, pp. 54-62, 2016.
9. [9] L. Xie, L. Lin, M. Yin, et al., “A novel surface defect inspection algorithm for magnetic tile,” Applied Surface Science, Vol.375, pp. 118-126, 2016.
10. [10] A. L. Cunha, J. P. Zhou, and M. N. Do, “Nonsubsampled contourlet transform: filter design and applications in denoising,” Proc. of IEEE Conf. on Image Processing, Genova, Italy, pp. 749-752, 2005.
11. [11] A. L. Cunha, J. Zhou, and M. N. Do, “The nonsubsampled contourlet transform: theory, design And applications,” IEEE Trans. on Image Processing, Vol.15, No.10, pp. 3089-3101, 2006.
12. [12] M. Hallbeyer, “Practical guidelines for choosing GLCM textures to use in landscape classification tasks over a range of moderate spatial scales,” Int. J. of Remote Sensing, Vol.38, No.5, pp. 1312-1338, 2017.
13. [13] E. S. Gadelmawla, “A vision system for surface roughness characterization using the gray level co-occurrence matrix,” NDT & E Int., Vol.37, No.7, pp. 577-588, 2004.
14. [14] P. Chen and S. Liu, “An Improved DAG-SVM for Multi-class Classification,” The 5th Int. Conf. on Natural Computation, IEEE Computer Society, pp. 460-462, 2009.
15. [15] H. Joutsijoki and M. Juhola, “DAGSVM vs. DAGKNN: An Experimental Case Study with Benthic Macroinvertebrate Dataset,” Machine Learning and Data Mining in Pattern Recognition: Proc. of the 8th Int. Conf. MLDM 2012, doi: 10.1007/978-3-642-31537-4, 2012.
16. [16] K. Crammer and Y. Singer, “On the algorithmic implementation of multiclass kernel-based vector machines,” J. of Machine Learning Research, Vol.2, No.2, pp. 265-292, 2001.
17. [17] B. Cao, Y. Xie, W. Gui, et al., “Integrated prediction model of bauxite concentrate grade based on distributed machine vision,” Minerals Engineering, Vol.53, No.10, pp. 31-38, 2013.
18. [18] J. C. Platt, N. Cristianini, and J. Shawe-Taylor, “Large Margin DAGs for Multiclass Classification,” Advances in Neural Information Processing Systems, Vol.12, No.3, pp. 547-553, 2000.
19. [19] J. Cai, X. Li, Y. Zhang, et al., “Improved DAGSVM hand gesture recognition approach,” J. Huazhong Univ. of Sci. & Teach., (Natural Science Edition), Vol.41, No.5, pp. 86-89, 2013.
20. [20] H. Ren and Z. Ma, “Strip Steel Surface Defect Recognition Based on Complex Network Characteristics,” Acta Automatica Sinica, Vol.37, No.11, pp. 1407-1412, 2011.