Abstract
In this paper, three successive feature reduction methods are employed to select good features for the automatic visual inspection of solder joints. This reduction strategy includes (1) a stability test to remove the features with unstable performance, (2) a separability examination to select the features with good classification capabilities, (3) a correlation analysis to delete the redundant features. Three sets of features are implemented in this feature reduction work: (1) a circular sub-area feature set is related to the intensity conditions within distinct areas in the joint image, (2) a moment of inertia feature set is based upon the intensity of pixels and their relative position in the image plane, (3) a surface curvature feature set analyses the three-dimensional joint topology. Initially 50 features are formulated based on the above strategy. The reduction technique deletes 39 features from this set because of instability, poor performance, and high correlation with other features. Finally, the remaining 11 feature are tested and shown to be superior to state-of-the-art identification methods.
Similar content being viewed by others
References
S. L. Spitz, ‘For higher yield: test or inspect bare PCBs?’,Electronic Packaging & Production,27(2), pp. 96–98, February 1987.
H. W. Markstein, ‘Bare board test and inspection assures product reliability’,Electronic Packaging & Production,26(4), pp. 70–74, April 1986,
R. T. Chin, C. A. Hariow, S. J. Dwyer, ‘Automatic visual inspection of printed circuit boards’,SPIE 155,Image Understanding Systems & Industrial Applications, pp. 199–213, 1978
Y. Hara, N. Akiyama and K. Karasaki, ‘Automatic inspection system for printed circuit boards’, inIEEE 1982 Conference on Industrial Applications of Machine Vision, IEEE Computer Society Press, Silver Spring, Maryland, pp. 62–70, 1982.
D. M. Walker, S. R. McNeill, G. Davis and M. A. Sutton, ‘A system for inspection of surface mount PC boards’, inProc. 1987 SME Conf. Vision, Dearborn, MI, pp. 11.1–11.2, June 1987.
W. H. Schwatz, ‘Vision systems for PC board inspection’,Assembly Engineering, pp. 18–21, August 1986.
R. Keeler, ‘Machine vision helps to acquire the image of quality’,Electronic Packaging & Production,25(1), pp. 116–123, January 1985.
R. Pound, ‘Image processing boosts the power of non-destructive testing’,Electronic Packaging & Production,25(6), pp. 98–104, June 1985.
H. W. Markstein, ‘Automatic optical inspection improves multilayer yields’,Electronic Packaging & Production,23(9), pp. 60–64, September 1983.
R. Pound, ‘Inspection equipment exposes quality of solder joints’,Electronic Packaging & Production,26(2), pp. 84–86, February 1986.
K. V. Pearson, ‘Printed circuit board fault detection and isolation using thermal imaging techniques’,SPIE 636 Thermal Imaging, pp. 122–125, 1986.
H. Danaher, ‘Thermal images show hybrids's defects’,Electronic Packaging & Production,26(9), pp. 34–35, 1986.
Y. Nakagawa, ‘Automatic visual inspection of solder joints on printed circuit boards’,SPIE 336,robot Vision, pp. 121–127, 1982.
W. E. McIntosh, ‘Automating the inspection of printed circuit boards’,Robotics Today,5 (3), pp. 75–78, June 1983.
P. J. Besl, E. J. Delp and R. Jain, ‘Automatic visual solder joint inspection’,IEEE Journal of Robotics and Automation,RA-1(1), pp. 42–56, March 1985.
J. G. Davy, ‘Wave solder defect standards model’,Proc. IPC Fall Meeting, San Francisco, CA, September 1984.
H. E. Schroeder, ‘Practical illumination concept and technique for machine vision applications’,Robot Sensors vol. 1 Vision, pp. 229–245, IFS Publications, Bedford, UK, 1986.
A. Novini, ‘Fundamentals of machine vision lighting’,SME technical paper, MS86-901, Michigan, 1986.
D. A. Hill, ‘Solving illumination problems’,Proceedings of the 4th International Conference on Robot Vision and Sensory Control, London, UK, pp. 37–44, October 1984.
K. R. Castleman,Digital Image Processing, Prentice-Hall, Englewood Cliffs, NJ, 1979.
R. C. Gonzalez and P. Wintz,Digital Image Processing, Addison-Wiley, Reading, MA, pp. 354–358, 1977.
D. J. Struik,Lectures on Classical Differential Geometry, Addison-Wiley, Cambridge, MA, 1950.
F. G. Peet and T. S. Sahota, ‘Surface curvature as a measure of image texture’,IEEE Transactions on Pattern Analysis and Machine Intelligence,PAMI-7, No. 6, pp. 734–738, November 1985.
P. Besl and R. Jain, ‘Intrinsic and extrinsic surface characteristics’,IEEE Proceedings on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Silver Springer, Maryland, pp. 226–233, June 1985.
R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis, New York: Wiley, 1973.
H. H. Manko,Solders and Soldering, McGraw-Hill, N. Y., 1979.
Bibliography
D. H. Ballard and C. M. Brown,Computer Vision, Prentice-Hall, NJ, 1982.
H. S. Na, ‘How artificial intelligence may impact vision’, inProceedings 1987 SME Conference on Vision, Dearborn, MI, pp. 8.1–8.8, June 1987.
R. T. Chin, ‘Automated visual inspection techniques and applications: a bibliography’,Pattern Recognition,15(4), pp. 343–357, 1982.
R. Maus and R. Allsup, Robotics: A Manager's Guide, John Wiley & Sons, NY, 1986.
R. W. Woodgate,Handbook of Machine Soldering, John Wiley, NY, 1983.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Driels, M.R., Lee, C.C. Feature selection for automatic visual inspection of solder joints. Int J Adv Manuf Technol 3, 3–32 (1988). https://doi.org/10.1007/BF02601831
Issue Date:
DOI: https://doi.org/10.1007/BF02601831