A Local Invariant Generalized Hough Transform Method for Integrated Circuit Visual Positioning

In this study, an local invariant generalized Houghtransform (LI-GHT) method is proposed for integrated circuit (IC) visual positioning. The original generalized Hough transform (GHT) is robust to external noise; however, it is not suitable for visual positioning of IC chips due to the four-dimensionality (4D) of parameter space which leads to the substantial storage requirement and high computational complexity. The proposed LI-GHT method can reduce the dimensionality of parameter space to 2D thanks to the rotational invariance of local invariant geometric feature and it can estimate the accuracy position and rotation angle of IC chips in real-time under noise and blur influence. The experiment results show that the proposed LI-GHT can estimate position and rotation angle of IC chips with high accuracy and fast speed. The proposed LI-GHT algorithm was implemented in IC visual positioning system of radio frequency identification (RFID) packaging equipment.

• Fei Long Wei
• Hua Yang
• Hai Tao Zhang
• Zhou Ping Yin

• Integrated Circuit Visual Positioning
• Generalized Hough Transform
• Local invariant Generalized Hough Transform
• ICpacking equipment.

[1] Brown L G. A survey of image registration techniques (J). ACM computing surveys (CSUR), 1992, 24(4): 325-376.
[2] Zitova B, Flusser J. Image registration methods: a survey (J). Image and vision computing, 2003, 21(11): 977-1000.
[3] Ballard D H. Generalizing the Hough transform to detect arbitrary shapes (J). Pattern recognition, 1981, 13(2): 111-122.
[4] P.V.C. Hough, A method and means for recognizing complex patterns, U.S. Patent 3069654, 1962.
[5] Lee H M, Kittler J, Wong K C. Generalized Hough transform in object recognition(C), Pattern Recognition, 1992. Vol. III. Conference C: Image, Speech and Signal Analysis, Proceedings. 11th IAPR International Conference on. IEEE, 1992: 285-289.
[6] Kassim A A, Tan T, Tan K H. Comparative studies of efficient generalized Hough transforms techniques (J). Image and Vision Computing, 1999, 17(10): 737-748.
[7] Ulrich M, Steger C. Empirical performance evaluation of object recognition methods (J). Empirical Evaluation Methods in Computer Vision, 2001: 62-76.
[8] Ulrich M, Steger C, Baumgartner A. Real-time object recognition using a modified generalized Hough transform (J). Pattern Recognition, 2003, 36(11): 2557-2570.
[9] Tsai D M. An improved generalized Hough transform for the recognition of overlapping objects (J). Image and Vision computing, 1997, 15(12): 877-888.
[10] Ser P K, Siu W C. Non-analytic object recognition using the Hough transform with the matching technique(C), Computers and Digital Techniques, IEE Proceedings. IET, 1994, 141(1): 11-16.
[11] Aguado A S, Montiel E, Nixon M S. Invariant characterization of the Hough transform for pose estimation of arbitrary shapes (J). Pattern Recognition, 2002, 35(5): 1083-1097.
[12] Canny J. A computational approach to edge detection (J). Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1986 (6): 679-698.
[13] Bing P, Hui-min X, Bo-qin X, et al. Performance of sub-pixel registration algorithms in digital image correlation (J). Measurement Science and Technology, 2006, 17(6): 1615.