Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Retinex-based Logarithm Transformation Method for Color Image Enhancement

컬러 이미지 화질 개선을 위한 Retinex 기반의 로그변환 기법

  • Kim, Donghyung (Dept. of Computer Science & Information Systems, Hanyang Women's Univ.)
  • 김동형 (한양여자대학교 컴퓨터정보과)
  • Received : 2018.03.12
  • Accepted : 2018.05.04
  • Published : 2018.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Images with lower illumination from the light source or with dark regions due to shadows, etc., can improve subjective image quality by using retinex-based image enhancement schemes. The retinex theory is a method that recognizes the relative lightness of a scene, rather than recognizing the brightness of the scene. The way the human visual system recognizes a scene in a specific position can be in one of several methods: single-scale retinex, multi-scale retinex, and multi-scale retinex with color restoration (MSRCR). The proposed method is based on the MSRCR method, which includes a color restoration step, which consists of three phases. In the first phase, the existing MSRCR method is applied. In the second phase, the dynamic range of the MSRCR output is adjusted according to its histogram. In the last phase, the proposed method transforms the retinex output value into the display dynamic range using a logarithm transformation function considering human visual system characteristics. Experimental results show that the proposed algorithm effectively increases the subjective image quality, not only in dark images but also in images including both bright and dark areas. Especially in a low lightness image, the proposed algorithm showed higher performance improvement than the conventional approaches.

광원 자체의 밝기가 낮거나 그림자 등의 이유로 어두운 영역을 포함하는 이미지는 Retinex 기반의 영상화질 개선기법을 통해 주관적 화질을 높일 수 있다. Retinex 이론은 인간의 시각 시스템이 장면을 인식할 때 특정 위치에서의 장면의 밝기를 인식하는 것이 아니라 주변과의 상대적인 밝기를 인식하는 특징을 적용한 방법으로 크게 SSR, MSR, MSRCR의 방법으로 나눌 수 있다. 제안하는 방법은 컬러복원단계를 포함하고 있는 MSRCR에 기반한 방법으로 크게 3단계로 구성되어 있다. 첫 번째 단계에서는 기존의 MSRCR 방법을 적용하고 두 번째 단계에서 MSRCR 출력의 동적 영역을 이미지의 히스토그램분포에 따라 조정한다. 마지막 단계에서는 인간의 시각특성을 고려한 로그변환함수를 이용하여 Retinex 출력 값을 디스플레이 동적영역으로 변환한다. 실험결과 제안하는 알고리즘은 전체적으로 어두운 이미지뿐만 아니라 밝은 영역과 어두운 영역을 모두 포함하는 이미지에서도 주관적 화질을 효과적으로 증가시키는 것을 볼 수 있다. 특히 낮은 밝기를 갖는 이미지의 경우 제안한 알고리즘은 기존의 방법들 보다 높은 성능향상을 보였다.

Keywords

References

  1. E. Land and J. McCann, "Lightness and retinex theory," Journal of the Optical Society of America, vol. 61, no. 1, pp. 1-11, 1971. DOI: https://doi.org/10.1364/JOSA.61.000001
  2. D. Marini and A. Rizzi, "Computational approach to color adaptation effects," Image and Vision Computing, vol. 18, no. 13, pp. 1005-1014. Oct. 2000. DOI: https://doi.org/10.1016/S0262-8856(00)00037-8
  3. E. Provenzi, M. Fierro, A. Rizzi, L. De Carli, D. Gadia, and D. Marini, "Random spray retinex: A new retinex implementation to investigate the local properties of the model," IEEE Transactions on Image Processing, vol. 16, no. 1, pp. 162-171, Jan. 2007. DOI: https://doi.org/10.1109/TIP.2006.884946
  4. D.J. Jobson, Z. Rahman, and G.A. Woodell, "Properties and performance of a center/surround retinex," IEEE Transactions on Image Processing, vol. 6, no. 3, Mar. 1997. DOI: https://doi.org/10.1109/83.557356
  5. A. Moore, J. Allman, and R. Goodman, "A real-time neural system for color constancy," IEEE Transactions on Neural Networks, vol. 2, no. 2, pp. 237-247, Mar. 1991. DOI: https://doi.org/10.1109/72.80334
  6. M. Bertalmio, V. Caselles, and E. Provenzi, "Issues about retinex theory and contrast enhancement," International Journal of Computer Vision, vol. 83, no. 1, pp. 101-119. June 2009. DOI: https://doi.org/10.1007/s11263-009-0221-5
  7. R. Kimmel, M. Elad, D. Shaked, R. Keshet, and I. Sobel, "A variational framework for retinex," International Journal of Computer Vision, vol. 52, no. 1, pp. 7-23, April 2003. DOI: https://doi.org/10.1023/A:1022314423998
  8. W. Ma, J.M. Morel, S. Osher, and A. Chien, "An L1-based variational model for retinex theory and its application to medical images," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 153-160, June 2011. DOI: https://doi.org/10.1109/CVPR.2011.5995422
  9. J.M. Morel, A.B. Petro, and C. Sbert, A PDE formalization of retinex theory, IEEE Transactions on Image Processing, vol. 19, no. 11, pp. 2825-2837, May 2010. DOI: https://doi.org/10.1109/ISKE.2017.8258829
  10. W. Tao, G. Ningsheng, and J. Guixiang, "Enhanced image algorithm at night of improved retinex based on HIS space," International Conference on Intelligent Systems and Knowledge Engineering (ISKE), pp. 1-5, Nov. 2017. DOI: https://doi.org/10.1109/ISKE.2017.8258829
  11. H. Tanaka, Y. Waizumi, and T. Kasezawa, "Retinex-based signal enhancement for image dark regions," IEEE International Conference on Signal and Image Processing Applications (ICSIPA). pp. 205-209, Sept. 2017. DOI: https://doi.org/10.1109/ICSIPA.2017.8120607
  12. S. Park, S. Yu, B. Moon, S. Ko, and J. Paik, "Low-light image enhancement using variational optimization-based retinex model," IEEE Transactions on Consumer Electronics, vol. vol. 63, no. 2, pp. 178-184, May 2017. DOI: https://doi.org/10.1109/ICCE.2017.7889233