Development of surface defect inspection algorithms for cold mill strip

냉연 표면흠 검사 알고리듬 개발에 관한 연구

  • 김경민 (고려대학교 정보통신기술공동연구소) ;
  • 박귀태 (고려대학교 전기공학과, 서울대 ERC-ACI연구) ;
  • 박중조 (경상대학교 제어계측공학과) ;
  • 이종학 (POSCO 기술연구소 SYSTEM 연구부 TEAM) ;
  • 정진양 (POSCO 기술연구소 SYSTEM 연구부 TEAM) ;
  • 이주강 (POSCO 기술연구소 SYSTEM 연구부 TEAM)
  • Published : 1997.04.01

Abstract

In this paper we suggest a development of surface defect inspection algorithms for cold mill strip. The defects which exist in a surface of cold mill strip have a scattering or singular distribution. This paper consists of preprocessing, feature extraction and defect classification. By preprocessing, the binarized defect image is achieved. In this procedure, Top-hit transform, adaptive thresholding, thinning and noise rejection are used. Especially, Top-hit transform using local min/max operation diminishes the effect of bad lighting. In feature extraction, geometric, moment and co-occurrence matrix features are calculated. For the defect classification, multilayer neural network is used. The proposed algorithm showed 15% error rate.

Keywords

References

  1. Digital Image Processing R. C. Gonzalez
  2. Digital Image Processing W. K. Pratt
  3. Computer and Robot Vision R. M. Haralick;L. G. Shapiro
  4. Image Processing, Analysis and Machine vision M. Sanka;V. Hlavac;R. Boyle
  5. Practical Computer Vision using C J. R. Parker
  6. Image Processing Algorithms I. Pitas
  7. Adaptive Pattern Recognition and Neural Network Y. H. Pao
  8. IEEE Trans. PAMI v.4 no.6 Automated visual inspection : A survey R. T. Chin
  9. Computer Vision and Image Understanding v.61 A survey of automated visual inspection T. S. Newman
  10. ICARCV'94 Advanced machine vision system for garment inspection P. W. Tse;P. S. Wu
  11. IEEE Trans. PAMI v.5 A real-time automated visual inspection system for hot steel slabs B. R. Suresh;R. A. Sundakowski;T. S. Levitt;J. E. Overland
  12. IEEE 11th Int. Conf. Pattern Recog. Automatic visual inspection of wood surfaces P. Alapuranen;T. Westman
  13. ICARCV'94 Automated visual inspection of painted metallic surfaces A. Ercil
  14. Description of Isys iS-2000 series Automated Surface Inspection System Isys Controls
  15. Surface Defect Inspector TOSPECTRON Series Toshiba Corporation
  16. Pattern Recognition Letters v.7 no.2 A modified fast parallel algorithm for thinning digital patterns Y. S. Chen;W. H. Hsu
  17. 퍼스컴을 이용한 화상처리 이문호
  18. 퍼스컴을 이용한 화상처리 이문호