Browse > Article
http://dx.doi.org/10.5302/J.ICROS.2015.15.0134

Auto Parts Visual Inspection in Severe Changes in the Lighting Environment  

Kim, Giseok (School of Computer Science and Engineering, Korea University of Technology and Education)
Park, Yo Han (School of Computer Science and Engineering, Korea University of Technology and Education)
Park, Jong-Seop (School of Computer Science and Engineering, Korea University of Technology and Education)
Cho, Jae-Soo (School of Computer Science and Engineering, Korea University of Technology and Education)
Publication Information
Journal of Institute of Control, Robotics and Systems / v.21, no.12, 2015 , pp. 1109-1114 More about this Journal
Abstract
This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.
Keywords
auto parts visual inspection; machine vision; adaboost; kNN; selective feature vector;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 G. Kim, S. Lee, and J. S. Cho, "A learning-based visualinspection system for part verification in a panoramasunroof assembly line using the SVM algorithm,"Journal of Institute of Control, Robotics and Systems (inKorean), vol. 19, no. 12, pp. 1099-1104, 2013.   DOI
2 S. Lee, G. Kim, and J. S. Cho, "Volts inspection of panorama sunroof frame using polar coordinated histogram," The 25th Workshop on Image Processing and Image Understanding (in Korean), p. 106, Jeju, 2013.
3 C. Cortes and V. N. Vladimir, "Support-vector networks," Machine Learning, 20, 1995.
4 Y. Freund and R. E. Schapire, "A Short Introduction toBoosting," Journal of Japanese Society for ArtificialIntelligence, vol. 14, no. 5, pp. 771-780, Sep. 1999.
5 N. Bhatia et al, "Survey of nearest neighbor techniques," International Journal of Computer Science and Information Security, vol. 8, no. 2, Jul. 2010.
6 N. Dalal and B. Triggs, "Histogram of oriented gradients for human detection," Proc. of CVPR 2005, vol. 1, pp. 886-893, Jun. 2005.
7 V. Vapnik, The Nature of Statistical Learning Theory, New York: Springer-Verlag, 1995.
8 X. Liang, "Effective method of pruning support vectormachine classifiers," Neural Networks, IEEE Transactionson, vol. 21, no. 1, pp. 26-38, Dec. 2009.
9 S. J. Lee and S. W. Kim, "Classifying scrach defects onbillets using image processing and SVM," Journal ofInstitute of Control, Robotics and Systems (in Korean),vol. 19, no. 3, pp. 256-261, Mar. 2013.   DOI