Quality inspection of lighting system used in surface quality inspection of brake pads

被引:0
|
作者
Xiang R. [1 ]
Xu H. [1 ]
机构
[1] College of Quality and Safety Engineering, China Jiliang University, Hangzhou
关键词
Design quality; Grayscale; Illumination; Lighting system; Machine vision;
D O I
10.19650/j.cnki.cjsi.J1804086
中图分类号
学科分类号
摘要
To realize the design quality inspection of the lighting system used in the machine vision system for surface quality inspection of brake pads, an automatic quantitative inspection method based on image grayscale indexes is designed. Brake pad images, illuminance mean values and standard deviations were captured under different working conditions of the illumination system; On the basis of image segmentation, 7 grayscale feature indexes of brake pads in grayscale images were extracted; The degree of gray distribution V and the gray distribution G were respectively used to represent the illuminance mean values and standard deviations based on correlation analysis between 7 grayscale feature indexes and illuminance mean values, standard deviations; The design quality of lighting systems can be inspected by using the testing model based on grayscale feature indexes V and G. The test results of 688 images of 8 brake pads captured under lighting conditions using 87 different lighting systems showed that the inspection model based on gray distribution degree V and gray distribution G can realize the quantitative inspection of the design quality of the lighting systems, and the correct rate was 90.99%. © 2018, Science Press. All right reserved.
引用
收藏
页码:248 / 257
页数:9
相关论文
共 22 条
  • [1] Li C.L., Guo B.Y., Jia X.Y., Quality auto-inspection method of stitch based on stereo vision, Journal of Computer-Aided Design & Computer Graphics, 27, 6, pp. 1067-1073, (2015)
  • [2] Su J.C., Tarng Y.S., Automated visual inspection for surface appearance defects of varistors using an 7 adaptive neuro-fuzzy inference system, The International Journal of Advanced Manufacturing Technology, 35, 7, pp. 789-802, (2008)
  • [3] Min Y.Z., Yue B., Ma H.F., Et al., Rail surface defects detection based on gray scale gradient characteristics of image, Chinese Journal of Scientific Instrument, 39, 4, pp. 220-229, (2018)
  • [4] Fan T., Zhu Q., Wang Y.N., Et al., Research on detection method of bottle bottom defects based on empty bottle detection robot system, Journal of Electronic Measurement and Instrumentation, 31, 9, pp. 1394-1401, (2017)
  • [5] Guo Z.L., Xing F., Lou X.P., Et al., Detection of appearance defect of starter based on machine vision, Journal of Electronic Measurement and Instrumentation, 32, 2, pp. 1-8, (2018)
  • [6] Lu E.H., Liu J., Wang W.F., Et al., Study on the performance assessment method of image indices associated with roughness, Chinese Journal of Scientific Instrument, 38, 8, pp. 2022-2029, (2017)
  • [7] Shahabi H.H., Ratnam M.M., Noncontact roughness measurement of turned parts using machine vision, The International Journal of Advanced Manufacturing Technology, 46, 1, pp. 275-284, (2010)
  • [8] Golkar E., Prabuwono A.S., Vision based length measuring system for ceramic tile borders, Procedia Technology, 11, 1, pp. 771-777, (2013)
  • [9] Zhi S., Zhao W.Z., Zhao W.H., Et al., Visual measurement method of pitch machine based on gear local image, Chinese Journal of Scientific Instrument, 39, 2, pp. 225-231, (2018)
  • [10] Zhang Q.F., Gao J., Research progress of lighting technology in machine vision, China Illuminating Engineering Journal, 22, 2, pp. 31-37, (2011)