A Vision Detection Algorithm for LIGA Part Assembly

This paper proposes a vision detection algorithm to acquire LIGA part’s edges based on an in-house multi-DOF manipulator for LIGA part assembly. Feature recognition based on maximum information entropy is proposed to solve the problem that high precision edge recognition under backlight source. In order to further improve vision recognition accuracy, edge feature recognition algorithm based on symmetrical edge is proposed to recognize the center line of the symmetrical parts when the quality of the image is poor.

[1]  Dan O. Popa,et al.  Micro and Mesoscale Robotic Assembly , 2004 .

[2]  Harry E. Stephanou,et al.  M3-Modular Multi-Scale Assembly System for MEMS Packaging , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  T. J. Ponman,et al.  Maximum entropy methods , 1984 .