Development of Defect Detection Algorithm in Cellular Denitration Catalyst

Abstract:

Denitration catalyst defect detection based on image processing plays a vital role in automated inspection of product quality. In this paper, we propose a defect detection algorithm based on image processing to inspect the cellular denitration catalyst. In pre-processing, Hough transform, morphological processing and connected component labeling are used to find the defect location. In the process of defect categories recognition, the Hu moments combined with geometrical features are used. Besides, support vector machine classifier is trained to detect the defect categories. The proposed algorithm shows high defect recognition accuracy achieving 96% overall.

• Periodical: Applied Mechanics and Materials (Volumes 716-717)
• Pages: 892-897
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.716-717.892
• Online since: December 2014
• Authors: Liang Ren Chen*, En Hui Zheng
• Keywords: Defect Classifier, Denitration Catalyst, Geometrical Feature, Hu Moments, Support Vector Machine (SVM)

References

[1] G. Rosati, G. Boschetti, A. Biondi, A. Rossi: Real-time defect detection on highly reflective curved surfaces. Optics and Lasers in Engineering 47(3-4), p.379–384 (2009).

DOI: 10.1016/j.optlaseng.2008.03.010

[2] D. Martin, D.M. Guinea, M.C. García-Alegre, E. Villanueva, D. Guinea: Multimodal defect detection of residual oxide scale on a cold stainless steel strip. Machine Vision and Applications 21(5), p.653–666 (2010).

DOI: 10.1007/s00138-010-0260-5

[3] A. Kumar, G.K. -H. Pang: Defect detection in textured materials using Gabor filters. IEEE Transactions on Industry Applications 38(2), pp.425-440 (2002).

DOI: 10.1109/28.993164

[4] L. Bissi, G. Baruffa, P. Placidi, E. Ricci, A. Scorzoni, P. Valigi: Automated defect detection in uniform and structured fabrics using Gabor filters and PCA. Journal of Visual Communication and Image Representation 24(7), pp.838-845 (2013).

DOI: 10.1016/j.jvcir.2013.05.011

[5] Zhang Xue-wu, Ding Yan-qiong, Lv Yan-yun, Shi Ai-ye, Liang Rui-yu: A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM. Expert Systems with Applications 38(5) (2011).

DOI: 10.1016/j.eswa.2010.11.030

[6] D. Weimer, H. Thamer, B. Scholz-Reiter: Learning Defect Classifiers for Textured Surfaces Using Neural Networks and Statistical Feature Representations. Procedia CIRP 7, pp.347-352 (2013).

DOI: 10.1016/j.procir.2013.05.059

[7] Duda, R. O. and P. E. Hart: Use of the Hough Transformation to Detect Lines and Curves in Pictures. Comm. ACM, Vol. 15, pp.11-15 (1972).

DOI: 10.1145/361237.361242

[8] H. Samet and M. Tamminen: Efficient Component Labeling of Images of Arbitrary Dimension Represented by Linear Bintrees. IEEE Transactions on Pattern Analysis and Machine Intelligence 10(4), pp.579-586 (1988).

DOI: 10.1109/34.3918

[9] M. K. Hu. Visual Pattern Recognition by Moment Invariants: IRE Trans. Info. Theory, vol. IT-8, p.179–187 (1962).