Computer Vision System for Defect Detection of Hot Rolling Products

International Journal of Computer Trends and Technology (IJCTT)          
© 2016 by IJCTT Journal
Volume-40 Number-2
Year of Publication : 2016
Authors : Ahmet ÇELİK


AhmetÇELİK "Computer Vision System for Defect Detection of Hot Rolling Products". International Journal of Computer Trends and Technology (IJCTT) V40(2):88-91, October 2016. ISSN:2231-2803. Published by Seventh Sense Research Group.

Abstract -
Detecting defect is the most required and important step in the production process. Computer aided defect detection can provide precise and fast solution. Detecting the defective products during production process is both cost-effective and prevents time-loss. In this study, a system is developed to detect defects during hot rolling operation using image processing methods.The rail and profile images are obtained by CMOS camera when they are rolled. By analyzing these images, different types of defects could be identifiedby using the different gray values for defective and non-defective regions. Defective areas cannot be seen clearly on the images with gray values. Therefore, image processing algorithms haveto be used on the obtained images. Defective regionscan be indicated by using colored segmentation. This study is applied in rolling mill of KarabukInc and is shown anfeature identification for rail and profile surface’s defects.

[1] H. Y. T. Ngan, G. K. H. Pang, N. H.C. Yung, Automated fabric defect detection-A review, Image and Vision Computing, 29 (2011) 442–458.
[2] J.W. Funck, Y. Zhong, D.A. Butler, C.C. Brunner, J.B. Forrer, Image segmentation algorithms applied to wood defect detection, Computers and Electronics in Agriculture, 41 (2003) 157-179.
[3] L. Shapiro, G. Stockman, Computer Vision, Prentice Hall Press, Washington, USA, 2001.
[4] Q. Luo,Y. He, Cost-effective and automatic surface defect inspection system for hot-rolled flat steel, Robotics and Computer -Integrated Manufacturing, 38 (2006) 16–30.
[5] F. J. de la Calle, F. G. Bulnes, D. F. García, A Parallel Genetic Algorithm for Configuring Defect Detection Methods, IEEE Latin America Transactions. 13 (2015) No. 5, 1462-1468.
[6] H. Zhai, H. Huang, S. He, W. Liu, Rice Paper Classification Study Based on Signal Processing and Statistical Methods in Image Texture Analysis, International Journal of Software Innovation, 2 (2014), No. 3, pp. 1-14.
[7] N. Pal, S. Pal, A review on image segmentation techniques, Pattern Recognition 26 (1993), 1277–1294.
[8] H. Cheng, X. Jiang, Y. Sun and J. Wang, Color image segmentation: Advances & prospects, Pattern Recognition, 34 (2001) No. 12, pp. 2259-2281.
[9] R. C. Gonzalez, E. Richard, Digital Image Processing, Publishing House of Electronics Industry, Beijing, China, 2007.
[10] X. Xie, A Review of Recent Advances in Surface Defect Detection using texture analysis techniques, Electronic Letters on Computer Vision and Image Analysis. 7 (2008) No 3, 1- 22.
[11] M. Elad, Sparse and Redundant Representations - From Theory to Applications in Signal and Image Processing, Springer Press, Haifa, Israel, 2010.
[12] R. Laganière, OpenCV 2.4 Computer Vision Application Programming Cookbook, PACKT Publishing, Birmingham, Mumbai. 2011.
[13] Orak M. I, Çelik A. Parallel Noise Removing Process on Hot Rolled Rail Images for Defect. Global Journal on Technology. 7 (2015) 136-143.
[14] Orak, I. M., Çelik, A., An algorithm (COLMSTD) for detection of defects on rail and profile surfaces, International Journal of Computer Science and Information Security (IJCSIS), 14 (2016), No: 4, 45-50.

Defect detection systems, Computer aided manufacturing, Image processing, Hot rollingsystems.