A New Algorithm of Weld Seam Detection Based on Mathematical Morphology

Abstract:

Weld seam tracking is the key technology of industrial robot. It satisfies accuracy and real-time demand. This paper presents a robust recognition algorithm for weld seam images based on mathematical morphology. This algorithm used the morphological filtering for image enhancement at first, and then applied Otsu threshold segmentation in local. Besides, it implemented region filling and morphological thinning operation to get the segmented weld seam. Finally, the Hough transform was adopted to detect the straight lines from the weld image. The results prove that this method not only can detect the seam tracking in real-time, but also can identify weld seam automatically.

• Periodical: Applied Mechanics and Materials (Volumes 397-400)
• Pages: 2124-2128
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.397-400.2124
• Online since: September 2013
• Authors: Bao Juan Zou, Na Fang, Ren Xian Zeng
• Keywords: Feature Extraction, Hough Transform (HT), Mathematical Morphology, Weld Seam Detection

References

[1] Jiluan Pan: Modern Arc Welding Control, China machine press, (2000).

[2] Lixin Sun, Shijie Dai and Kai Li, Research on the image processing of multi-pass seam based on line structure light. Transaction of the china welding institution, 2002, 23(3), pp.53-70.

[3] J. Jiang, J. Wu and Z. Cai, The application of wavelet transform in welding seam recognition. Proceedings of the 6th International Conference on Electronic Measurement and Instruments, vol. 1-3, pp.970-974, August 2003, Taiyuan China.

[4] Y. Zhai, H. Zhang and J. Che, Identification and measure of weld seam in multi-layer and multi-pass weld. Proceedings of the 6th International Conference on Electronic Measurement and Instruments, vol. 1-3, pp.910-913, August 2003, Taiyuan China.

[5] Xinyu Shu, Guorong Wang and Suyi Liu, Method for seam image process based on mathematical morphology. Electric welding machine, 2006, 36(3), pp.48-51.

[6] Qing Liu, Jiuwen Zhang , Zhixian Wen and Buda Zhang, On handing mathematical morphology in images. Joural of Tianshui Normal University, 2004, 24(2), pp.29-33.

[7] Ronghua Hu, Guoping Liu and Hua Zhang, Application of image processing based on the grayscale morphology in weld detection. Coputer engineering and applications, 2005, (27), pp.209-211.

[8] Otsu, N. A threshold selection method from gray-level histohram. IEEE Transactions on systems, men, and cybernetics, vol. 9, No. 1, 1979, pp.62-66.

DOI: 10.1109/tsmc.1979.4310076

[9] Juan Zhu, Yanying Liu and Yanjie Wang, A new line segment detection method based on Hough transform. Microel Electronics &Computer, 2008, 25(12), pp.60-63.

[10] Rujiao Duan, Wei Zhao and Songling Huang, Arapid line segment detection method based on Hough transform. Chinese Journal of Scientific Instrument, 2010, 31(12), pp.2774-2780.