Research on Solder Joints Quality Detection of Auto Parts Based on Biological Vision Feature

Abstract:

Detecting of the auto parts solder joints quality is always a technological difficulty in the production line, the key point is how to exact the parts feature which is tested. New quality detection method for the auto parts soldered joints is presented based on biology vision feature. First the Gabor filter banks which have the emulation of biological vision is used to filter the detected image with eight different directions. Then the biggest powers of all pixel points are chosen to be the solder joints feature and classified by support vector machine (SVM). The experimental results show that the algorithm has higher accuracy as an effective quality detection method. It can be a useful reference to the auto parts solder joints quality testing of engineering application.

• Periodical: Advanced Materials Research (Volumes 712-715)
• Pages: 2385-2388
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.712-715.2385
• Online since: June 2013
• Authors: Chuan Lin*, Xiao Feng Lv, Yi Jun Cao, Jiang Hua Wei, Cong Lin
• Keywords: Auto Parts, Biological Vision, Detection, Quality of Solder Joint

References

[1] Chunyue Huang: Inspection and intelligent discrimination based on solder joint virtual evolving technology. PhD thesis,Xidian University (2007). (In Chinese)

[2] Toshifuni Hond ed al: Automated Visual Inspection Algorithm for solder joint of surface mount devices based on three-dimensional shape analysis. Proceeding of MVA '96 IAPR Workshop on Machine Vision Applications. (1996), pp.12-14.

[3] Debao Peng: Application of computer vision technology in PCB automatic detection system design and development. PhD thesis, National Tsing Hua University in Taiwan. 2001. （In Chinese）

[4] Kim T-H, Cho T-H, Moon YS, Park SH: Visual inspection system for the classification of solder joints. Pattern Recognition. Vol. 4 (1999), pp.565-575.

DOI: 10.1016/s0031-3203(98)00103-4

[5] C. Chang and S. Chatterjee: Ranging through gabor logons-a consistent, hierarchical approach. IEEE Transactions on Neural Networks. Vol. 4(1993), pp.827-843.

DOI: 10.1109/72.248460

[6] T. C. Folsom and R. B. Pinter: Primitve features by steering, quadrature, and scale. IEEE Transcations on Pattern Analysis and Machine Intelligence. Vol. 20(1998), pp.1161-1173.

DOI: 10.1109/34.730552

[7] M. G. Milanova, A.S. Elmaghraby, M. P. Wachowiak and A. Campilho: A comutational model of visual cortex receptive fields using spatio-temporal filters. In proceedings of the 2000 IEEE/EMBS Conference on Information Technology Applications in biomedicine. (2000) , pp.129-134.

DOI: 10.1109/itab.2000.892364

[8] Cosmin Grigorescu, Nicolai Petkov and Michel A.Westenberg: Contour detection based on nonclassical receptive field inhibition. IEEE Transactions on image processing.vol. 12, no. 7,July 2003 729-739. Vol. 12(2003), pp.729-739.

DOI: 10.1109/tip.2003.814250