A study on inspection area using neural network for vision systems

비젼 시스템에서 신경 회로망을 이용한 검사 영역에 관한 연구

  • Oh, Je-Hui (Dept.of Mechanical Engineering, Wonkwang University) ;
  • Cha, Young-Youp (Dept.of Mechanical Engineering, Wonkwang University)
  • 오제휘 (원광대학교 기계공학부) ;
  • 차영엽 (원광대학교 기계공학부)
  • Published : 1998.06.01

Abstract

A FOV, that stands for "Field Of View", refers to the maximum area where a camera could be wholly seen. If a FOV of CCD camera cannot the cover overall inspection area, the overall inspection area should be divided into sub-areas of size FOV. In this paper, we propose a new neural network-based FOV generation method by using a newly modified self-organizing map(SOM) which has multiple structure based on a self-organizing map, and uses new training rule that is composed of the movement, creation and deletion terms. Then, experiment results using real PCB indicate the superiority of the method developed in this study to the existing sequential method.al method.

Keywords

References

  1. Computer Vision and Image Understanding v.61 no.2 A survey of automated visual inspection T. S. Newman;A. K. Jain
  2. Mechatronics v.7 no.2 A neural network approach to extended gaussian image based solder joint inspection Y. K. Ryu;H. S. Cho
  3. Mechatronics v.6 no.6 A calibration and range-data extraction algorithm of an omnidirectional laser range finder for free ranging mobile robot Y. Y. Cha;D. G. Gweon
  4. 한국정밀공학회지 v.14 no.8 부품 조립 공정에서 경로의 최적화 알고리즘 오제휘;차영엽
  5. 비젼을 이용한 PCB 납땜 검사장치의 개발 김철우
  6. Proc. of the IEEE v.78 no.9 The self-organizing map T. Kohonen
  7. Pattern recognition with neural networks in C++ A. S. Pandya;R. B. Macy