A new algorithm for a three-axis auto-alignment system using vision inspection

Abstract In this study, a new algorithm was developed for a vision-aided auto-alignment system. The proposed algorithm makes use of the correlation between the input signals and the output feedback. Through matrix transformation, the algorithm establishes the characteristic matrix of the system function between input and output signals. The search for this characteristic matrix involves inputs of real-time movement commands. With movement of fiducial images captured by CCD, the characteristic matrix can be obtained after image processing and matrix transformation. Alignment operation using the proposed algorithm will only make use of the coordinate system within the field of view of CCD. With the difference in fiducial mark as well as positional variation obtained, the alignment commands can be fed to the three-axis motion control mechanism to compensate for the difference in position and orientation, thus, achieving accurate alignment. Results from over hundreds of experimental runs have proved that rapid automatic and precise alignment can be achieved using a vision-aided system integrated with the proposed algorithm.

[1]  J. M. Parker A robust machine vision system design to facilitate the automation of surface appearance inspections , 2001, 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Proceedings (Cat. No.01TH8556).

[2]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[3]  A robust face identification against lighting fluctuation for lock control , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[4]  Yasuhiko Hara,et al.  Automatic Inspection System for Printed Circuit Boards , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Horst Bischof,et al.  Efficient alignment of fingerprint images , 2002, Object recognition supported by user interaction for service robots.

[6]  Li Xin,et al.  The application of machine vision in inspecting position-control accuracy of motor control systems , 2001, ICEMS'2001. Proceedings of the Fifth International Conference on Electrical Machines and Systems (IEEE Cat. No.01EX501).

[7]  Shang-Hong Lai Robust Image Matching under Partial Occlusion and Spatially Varying Illumination Change , 2000, Comput. Vis. Image Underst..

[8]  Ehud Weinstein,et al.  System identification using nonstationary signals , 1996, IEEE Trans. Signal Process..

[9]  Lee E. Weiss,et al.  Dynamic sensor-based control of robots with visual feedback , 1987, IEEE Journal on Robotics and Automation.

[10]  Shang-Hong Lai,et al.  A Hybrid Image Alignment System for Fast and Precise Pattern Localization , 2002, Real Time Imaging.