Visual positioning of rectangular lead components based on Harris corners and Zernike moments

Abstract

With the increasing necessities for reliable printed circuit board (PCB) product, there has been a considerable demand for high speed and high precision vision positioning system. To locate a rectangular lead component with high accuracy and reliability, a new visual positioning method was introduced. Considering the limitations of Ghosal sub-pixel edge detection algorithm, an improved algorithm was proposed, in which Harris corner features were used to coarsely detect the edge points and Zernike moments were adopted to accurately detect the edge points. Besides, two formulas were developed to determine the edge intersections whose sub-pixel coordinates were calculated with bilinear interpolation and conjugate gradient method. The last experimental results show that the proposed method can detect the deflection and offset, and the detection errors are less than 0.04° and 0.02 pixels.

Keywords

visual positioning / Harris corners / Zernike moments / edge detection / sub-pixel / image registration

References

[1] LinC S, LueL W. An image system for fast positioning and accuracy inspection of ball grid array boards [J]. Microelectronics Reliability, 2001, 41(1): 119-128

[2] ShangH L, MingF. A hybrid image alignment system for fast and precise pattern localization [J]. Real-Time Imaging, 2002, 8(1): 23-33

[3] YehC H, ShenT C, WuF C. A case study: Passive component inspection using a 1D wavelet transform [J]. International Journal of Advanced Manufacturing Technology, 2003, 22(11/12): 899-910

[4] XieY-m, LiuQiang. Research on locating algorithm of vision alignment system in automatic high precision chip mounter [J]. Optical Technique, 2008, 34(3): 449-454

[5] ZhangW-j, LiD, YeFeng. Vision-based inspection algorithm for chip components [J]. Journal of South China University of Technology: Natural Science Edition, 2010, 38(1): 65-69

[6] LyversE P, MitchellO R, AkeyM L, ReevesA P. Subpixel measurements using a moment-based edge operator [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(12): 1293-1308

[7] GhosalS, MehrotraR. Orthogonal moment operators for subpixel edge detection [J]. Pattern Recognition, 1993, 26(2): 295-306

[8] GaoS-y, ZhaoM-y, ZhangL, ZouY-yuan. Improved algorithm about subpixel edge detection of image based on Zernike orthogonal moments [J]. Acta Automatica Sinica, 2008, 34(9): 1163-1168

[9] GuanB-q, YuX-r, WangS-gang. An inspection method of component type based on moment features and chain code [J]. Journal of Shanghai Jiao Tong University, 2005, 39(6): 969-974

[10] HeL-f, ChaoY-y, SuzukiK, WuK-sheng. Fast connected-component labeling [J]. Pattern Recognition, 2009, 42(9): 1977-1987

[11] PanY-f, HouX-w, LiuC-lin. A hybrid approach to detect and localize texts in natural scene images [J]. IEEE Transactions on Image Processing, 2011, 20(3): 800-813

[12] WuK-s, OtooE, SuzukiK. Optimizing two-pass connected-component labeling algorithms [J]. Pattern Analysis and Applications, 2009, 12(2): 117-135

[13] HsiaoP Y, LuC L, FuL C. Multilayered image processing for multiscale Harris corner detection in digital realization [J]. IEEE Transactions on Industrial Electronics, 2010, 57(5): 1799-1805

[14] GueguenL, PesaresiM. Multiscale Harris corner detector based on differential morphological decomposition [J]. Pattern Recognition Letters, 2011, 32(14): 1714-1719

[15] ChenZ, SunS-kuo. A Zernike moment phase-based descriptor for local image representation and matching [J]. IEEE Transactions on Image Processing, 2010, 19(1): 205-219

[16] DaF-p, ZhangHu. Sub-pixel edge detection based on an improved moment [J]. Image and Vision Computing, 2010, 28(12): 1645-1658

[17] CuiJ W, TanJ B, ZhouY, ZhangH. Improvement of vision measurement accuracy using Zernike moment based edge location error compensation model [C]. Journal of Physics: Conference Series Harbin, 2007ChinaIOP Publishing1353-1360

[18] HagerW W, ZhangH-chao. A new conjugate gradient method with guaranteed descent and an efficient line search [J]. SIAM Journal on Optimization, 2005, 16(1): 170-192

[19] YuanG-l, LuX-w, WeiZ-xin. A conjugate gradient method with descent direction for unconstrained optimization [J]. Journal of Computational and Applied Mathematics, 2009, 233(2): 519-530

[20] PeiY-j, WuH, YuJ, CaiG-hui. Effective image registration based on improved Harris corner detection [C]. International Conference on Information Networking and Automation Kunming, 2010ChinaIEEE93-96

[21] ManuelG S, ThurmanS T, FienupJ R. Efficient subpixel image registration algorithms [J]. Optics Letters, 2008, 33(2): 156-158

[22] WyawahareM V, PatilP M, AbhyankarH K. Image registration techniques: An overview [J]. International Journal of Signal Processing, 2009, 2(3): 11-26

[23] WenG-j, LuJ-j, WangJ-yang. An automated method for feature-based image registration with high-accuracy [J]. Journal of Software, 2008, 19(9): 2293-2301

[24] LiQ-l, WangG-y, LiuJ-g, ChenS-bo. Robust scale-invariant feature matching for remote sensing image registration [J]. IEEE Geoscience and Remote Sensing Letters, 2009, 6(2): 287-291

[25] GhosalS, MehrotraR. Detection of composite edges [J]. IEEE Transactions on Image Processing, 1994, 3(1): 14-25