Research on Geometric Positioning Algorithm of Vision System in High Speed and High Precision Chip Mounter

Abstract:

Considering features of PCB marks and components image, in order to search a consistent location for reference images in multidimensional parameter space, the algorithm of geometric characteristic recognition location is proposed. Geometric location algorithm mainly include model training and real-time search. Compared to edge location and traditional localization methods, which not only adapt the gray-scale linearity and the gray non-linear changes, but also support changes in scale and perspective. Numerical results shows that the position deviation of geometric positioning algorithm is less than 0.5 pixel, the angle deviation is less than 0.5 degree. This algorithm is robust, simple, practical and it is better than the traditional location method.

• Periodical: Applied Mechanics and Materials (Volumes 519-520)
• Pages: 667-671
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.519-520.667
• Online since: February 2014
• Authors: Yin Hua Huang*, Dong Bo Li
• Keywords: Chip Mounter, Geometric Location, Model Training, Multidimensional Parameter Space, Vision System

References

[1] Lecarpentier G, Mottet J, et al. High accuracy machine automated assembly for opto electronic [C]. Electronic Components and Technology Conference, Las Vegas, NV, USA. IEEE, 2000. 1-4.

DOI: 10.1109/ectc.2000.853099

[2] Jiang H, Lian X, et al. Machine vision inspection system and accurate orientation technology of automatic BGA ball mounting [J]. Journal of the Chinese Society of Mechanical Engineers, Transactions of the Chinese Institute of Engineers, Series C, 2005, 26(6): 779-784.

[3] Li Chen, Kim-Hui Yap. An Efficient Technique for Subpixel Image Registration Under Noisy Conditions [J]. IEEE Trans. System, Man, and Cybernetics, 2008, 38(4).

DOI: 10.1109/tsmca.2008.923055

[4] G. Tzimiropoulos, V. Argyriou, Tania Stathaki. Robust FFT-Based Scale-Invariant Image Registration with Image Gradient [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2010, 32(10).

DOI: 10.1109/tpami.2010.107

[5] Carlos Martinez-Ortiz, Jovisa Zunic. Curvature weighted gradient based shape orientation [J]. Pattern Recognition, 2010, 43: 3035-3041.

DOI: 10.1016/j.patcog.2010.03.026

[6] T. Alexandropoulos, S. Boutas, V. loumos and E. Kayafas. Template-guided inspection of arbitrarily oriented targets[J]. IET Computer Vision, 2008, 2(3): 150-163.

DOI: 10.1049/iet-cvi:20070025

[7] Shou-Der Wei and Shang-Hong Lai. Robust and Efficient Image Alignment Based on Relative Gradient Matching[J]. IEEE Tranctions on Image Processing, 2006, 15(10): 2936-2943.

DOI: 10.1109/tip.2006.877500

[8] Murat Balci and Hassan Foroosh. Subpixel estimation of shifts directly in the Fourier domain [J]. IEEE tranctions on Image Processing, 2009, 18(10): 2340-2354.

DOI: 10.1109/tip.2006.873457

[9] Shih Ching-Long, Ruo Chi-Wei, Sheu Hsin-Teng. Locating and Checking of BGA Pin's Position Using Gray Level[J]. International Journal of Advanced Manufacturing Technology, 2005, 26(5): 491-498.

DOI: 10.1007/s00170-003-1617-y

[10] Ivan Markovsky and Sasan Mahmoodi. Least-Squares Contour Alignment [J]. IEEE Signal Processing Letters, 2009, 16(1): 41-44.

DOI: 10.1109/lsp.2008.2008588

[11] Hong Wang , Shi Wang et al . Research on Angle Location of Fractal Features [J]. Journal of computer aided design and graphics , 2002, 14(4): 292-295.