The Journal of the Korea Contents Association (한국콘텐츠학회논문지)

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Color Image Compensation Method using Advanced Image Formation Model and Adaptive Filter

개선된 영상생성 모델과 적응적 필터를 이용한 칼라 영상 보정방법

  • 최호형 (경북대학교 정보통신학과) ;
  • 윤병주 (경북대학교 전자전기컴퓨터학부)
  • Received : 2009.08.05
  • Accepted : 2009.10.23
  • Published : 2009.12.28
Download PDF
⟨ Previous Next ⟩

Abstract

Color rendition method is necessary for improving the low contrast images which are achieved by PDA, mobile phone camera or PC camera. There are some methods for color rendition. However, after correcting the color, image quality degradations, such as graying-out, halo-artifact and color noise, may occur. In order to overcome these problems, this paper proposes a retinex-based color rendition method. The proposed method uses the HSV color coordinate system to avoid the graying-out, and the advanced image formation model to reduce the halo-artifact in which the image is divided into three components as the global illumination, the local illumination, and reflectance. The experiment results show that the proposed method yields better performance of color correction over the conveniently method.

일반적으로 PDA, 모바일 폰 카메라, PC 카메라 등으로 촬영된 영상은 촬영 장비의 생동 폭의 한계로 인해 낮은 영상 대비를 갖는 영상들이 획득된다. 이러한 이유로 영상 개선 방법은 여러 가지의 영상 촬영 장비를 이용해 촬영된 영상들의 개선을 위해 필요하다. 영상 개선을 위한 몇 가지의 방법들이 제안되었으나, 후광효과(halo-artifact), 회색계의 왜곡(graying-out), 칼라 잡음(color noise) 등의 영상 왜곡이 발생한다. 이러한 문제를 해결하기 위해, 본 논문은 레티넥스 기반 영상 향상 방법을 제안하며, 회색계의 왜곡을 줄이기 위해 HSV 칼라 좌표계를 사용하며, 후광효과를 줄이기 위해 영상을 전역조명성분, 국부조명성분, 반사성분으로 나누는 개선된 영상 생성모델을 적용한다. 실험 결과는 제안한 방법이 다른 방법들 보다 성능이 우수함을 보여준다.

Keywords

References

  1. Daniel J. Jobson and Zia-ur Rahman, "Properties and Performance of a Center/Surround Retinex," IEEE Trans. Image Process, Vol.6, No.3, pp.451-492, 1997(3). https://doi.org/10.1109/83.557356
  2. D. J. Jobson, Z. Rahman, and G. A. Woodell, "A Multiscale Retinex for Bridging the Gap between Color Images and The Human Observation," IEEE Trans. Image Process, Vol.6, No.7, pp.965-976, 1997(7). https://doi.org/10.1109/83.597272
  3. 최두현, 장익훈, 김남철, "개선된 영상생성 모델에 기반한 칼라 영상 향상," 대한전자공학회 논문지 제43권, 제6호, pp.65-84, 2006(11).
  4. D. H. Choi, I. H. Jang, M. H. Kim, and N. C. Kim, "Color image enhancement based on single-scale retinex with a JND-based nonlinear filter," in Proc. IEEE Int. Symp. Circuits and Syst., New Orleans, USA, pp.3948-3951, 2007(3). https://doi.org/10.1109/ISCAS.2007.378664
  5. L. Meylan, D. Alleysson, and S. Süsstrunk, "Model of retinal local adaptation for the tone mapping of color filter array images," J. Opt. Soc. Am. A, Vol.24, No.9, pp.2807-2816, 2007(9). https://doi.org/10.1364/JOSAA.24.002807
  6. I. S. Jang, K. H. Park and Y. H. Ha, "Color Correction by Estimation of Dominant Chromaticity in Multi-Scaled Retinex," Jurnal of Imaging Science and Technology, Vol.53, No.5, 050502-050502-11, 2009. https://doi.org/10.2352/J.ImagingSci.Technol.2009.53.5.050502
  7. C. Ke, "Adaptive Smoothing Via Contextual and Local Discontinuities," IEEE Transactions on Pattern analysis and machine intelligence, Vol.27, No.10, pp.1552-1567, 2005(10). https://doi.org/10.1109/TPAMI.2005.190
  8. Y. K. Park and J. K. Kim, "A New Methodology of Illumination Estimation/Normalization for Robust Face Recognition," IEEE international Conference on image Processing, 2007(9).
  9. Peter J. Burt and Edward H. Adelson, "The Laplacian Pyramid as a Compact Image Code," IEEE Transaction on communications, Vol.COM-31, No.4, 1983(4). https://doi.org/10.1109/TCOM.1983.1095851
  10. Alan Watt, 3D Computer Graphics, third edition Addison Wesley, 2000.
  11. Daniel J. Jobson, Zia-Ur Rahman, Glenna A. Woodell, and Glenn D. Hines, "A Comparison of Visual Statistics for The Image Enhancement of FORESITE Aerial Images with Those of Major image Class," Visual Information Processing XIV, Proc. SPIE, 6246, 2006.