이산 웨이블릿 합성 영상을 이용한 철강 후판 검사의 조명 메커니즘에 관한 연구

A Study on Illumination Mechanism of Steel Plate Inspection Using Wavelet Synthetic Images

  • 조은덕 (한국교통대학교 대학원) ;
  • 김경범 (한국교통대학교 기계자동차항공공학부)
  • Cho, Eun Deok (Graduate school, Korea National University of Transportation) ;
  • Kim, Gyung Bum (Aeronautical & Mechanical Design Engineering, Korea National University of Transportation)
  • 투고 : 2018.05.31
  • 심사 : 2018.06.19
  • 발행 : 2018.06.30

초록

In this paper, surface defects and typical illumination mechanisms for steel plates are analyzed, and then optimum illumination mechanism is selected using discrete wavelet transform (DWT) synthetic images and discriminant measure (DM). The DWT synthetic images are generated using component images decomposed by Haar wavelet transform filter. The best synthetic image according to surface defects is determined using signal to noise ratio (SNR). The optimum illumination mechanism is selected by applying discriminant measure (DM) to the best synthetic images. The DM is applied using the tenengrad-euclidian function. The DM is evaluated as the degree of contrast using the defect boundary information. The performance of the optimum illumination mechanism is verified by quantitative data and intuitive image looks.

키워드

참고문헌

  1. Neogi, N, Dusmanta, K. and Pranab, K., "Review of Vision-Based Steel Surface Inspection Systems", EURASIP Journal on Image and Video Processing, pp. 1-5, 2014.
  2. Cho, E. D. and Kim, G. B., "Fused Illumination Mechanism Design for Steel Plate Surface Inspection" Journal of KSDT Vol. 16, No. 3, pp. 14-19, 2017.
  3. Li, W. C., Tsai, D. M., "Wavelet-Based Defect Detection in Solar Wafer Images with Inhomogeneous Texture", Pattern Recognition, Vol. 45, pp. 742-756, 2012.
  4. Gonzales R C, Woods R E and Eddins S L, "Digital Image Processing ", 2017.