Image Capturing and Segmentation Method for Characters Marked on Hot Billets

Abstract:

Real-time detecting information marked on billets is important for automatically manufacturing and management in steelworks. But due to the tough production environments in steel enterprises, capturing and identifying characters marked on hot billets have many challenges. This paper presents a real-time image capturing and segmenting method with machine vision for characters marked on hot billets, and characters area is located based on color information of images. Furthermore, considering the marked characters are often slant, we proposed a kind of characters skew correction method to adjust the alignment of characters, and then segment characters into singles for recognition. Finally, with the proposed method, we have conducted some experiments in Baosteel Company. The result shows that our method can achieve 97% segmentation rate if we select proper image acquisition device and preprocessing algorithm. Additionally, it provides a new way for steel enterprise real-time capturing and segmenting marked characters image.

• Periodical: Advanced Materials Research (Volumes 945-949)
• Pages: 1830-1836
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.945-949.1830
• Online since: June 2014
• Authors: Qi Jie Zhao*, Peng Cao, Qing Xu Meng
• Keywords: Hot Billets, Image Capturing, Image Segmentation, Machine Vision

References

[1] Q.J. Zhao, P. Cao, D.W. Tu, Toward intelligent manufacturing: label characters marking and recognition method for steel products with machine vision", Advances in Manufacturing, 2014(Online in press), DOI: 10. 1007/s40436-014-0057-2.

DOI: 10.1007/s40436-014-0057-2

[2] H.B. Jia, Y. L. Murphey, J. J. Shi, An Intelligent Real-time Vision System for Surface Defect Detection, Proceedings of the 17th International Conference on Pattern Recognition, Vol. 4, 2004, pp.239-242.

DOI: 10.1109/icpr.2004.1334512

[3] J.N. Zhu, Yasushi Mae, Mamoru Minami, Finding and Quantitative Evaluation of Minute Flaws on Metal Surface Using Hairline, IEEE Transactions on Industrial Electronics, Vol. 54, no. 3, 2007, pp.1420-1429.

DOI: 10.1109/tie.2007.893050

[4] S.G. Park, J.H. Lee, Development of real-time character recognition system for the steel-iron plant, Proceedings of International Conference on Hybrid Information Technology, Vol. 1, Cheju Island, 2006, pp.287-292.

DOI: 10.1109/ichit.2006.253501

[5] C.Y. Park, S.C. Won , Development of Recognition System for Billet Identification, Proceedings of SICE Annual Conference, Takamatsu, Japan, 2007, pp.68-71.

DOI: 10.1109/sice.2007.4420952

[6] Tetsuro Yanagita, Toshimitsu Tanaka, Akio Toshima, A neural network recognition system for machine printed characters on coils, Conference Record of the 1995 IEEE Industry Applications Conference Thirtieth IAS Annual Meeting, Orlando, FL, vol. 2, 1995, pp.1795-1799.

DOI: 10.1109/ias.1995.530524

[7] S. B. Shim, S. H. Choi, S. Woo, Text Localization using Valid Optical Flow for Recognition of Slab Numbers, Proceedings of International Conference on Control, Automation and Systems, Gyeonggi-do, 2010, pp.324-329.

DOI: 10.1109/iccas.2010.5670208

[8] J. H. Cai, G. X. Zhang, Z. K. Zhou, Design of On-line Automatic Vision Inspection System for Steel Billet Characters, Chinese Journal of Sensors and Actuators. Vol. 19, No. 3, 2006, pp.686-689(In Chinese).

[9] Kezheng Lin, Caihua Zhang, Pie Liu, Image Retrieval Based on Sub-block Dominant Color Matching. Computer Engineering, Vol. 36, No. 13, 2010. (In Chinese).