DOI QR코드

DOI QR Code

Enhancement of Faded Images Using Integrated Compensation Coefficients Based on Multi-Scale Gray World Algorithm

다중크기 회색계 알고리즘 기반의 통합된 보정 계수를 이용한 바랜 영상 개선

  • Kyung, Wang-Jun (Kyungpook National University, School of Electronics Engineering) ;
  • Kim, Dae-Chul (Kyungpook National University, School of Electronics Engineering) ;
  • Ha, Yeong-Ho (Kyungpook National University, School of Electronics Engineering)
  • Received : 2014.05.01
  • Accepted : 2014.08.08
  • Published : 2014.08.31

Abstract

Fading effect of old pictures and printings is shown up differently according to the ink property, temperature, humidity, illuminants, and so on. Faded image enhancement techniques based on illuminant estimation are proposed such as the gray world algorithm and white patch retinex methods. However, conventional simple operators are not suitable for enhancing faded images because partial fading effect is appeared differently. Thus, this paper presents a color enhancement algorithm based on integrating correction coefficients for faded images. First, the proposed method adopts local process by using multi-scale average mask. The coefficients for each multi-scale average mask are obtained to apply the gray world algorithm. Then, integrating the coefficients with weights is performed to calculate correction ratio for red and blue channels in the gray world assumption. Finally, the enhanced image is obtained by applying the integrated coefficients to the gray world algorithm. In the experimental results, the proposed method reproduces better colors for both wholly and partially faded images compared with the previous methods.

오랜 시간 보관된 사진 및 인쇄물의 색 바랜 현상은 염료의 특성, 보관 온도, 습도 및 광원 등의 환경적 요인에 따라 다르게 나타난다. 이러한 바랜 영상의 보정을 위해 회색계 알고리즘(gray world algorithm) 또는 WR(white patch retinex)과 같은 전역적 광원 추정을 기반으로 한 방법이 제안되었다. 그러나 색 바랜 현상은 지역적으로 다르게 나타나므로 기존의 전역적 방법으로는 잘 보정되지 않는다. 이에 본 논문에서는 바랜 영상의 지역적 보정을 위해 보정계수 통합 기반 색 보정 알고리즘을 제안하였다. 먼저, 제안한 방법은 다중 크기의 평균 필터를 적용해 지역적인 처리를 수행하고, 회색계 알고리즘을 기반으로 한 영상의 보정계수를 얻는다. 다음으로, R과 B 채널에 적용하기 위해 계산된 다중 크기의 보정계수들을 가중처리하여 합하고, 이 가중처리된 보정계수를 회색계 알고리즘 처리를 통해 결과 영상을 얻는다. 그 결과 제안한 방법은 전역적, 지역적으로 바랜 영상들에 대해 기존의 방법들보다 나은 보정 결과를 보였다.

Keywords

References

  1. F. S. Frey, R. Gschwind, and L. Rosenthaler, "Electronic imaging, a tool for the reconstruction of faded color photographs and motion pictures," in Proc. Color Imaging Conf., pp. 39-44, Jan. 1996.
  2. H. Wilhelm, "A review of accelerated test methods for predicting the image life of digitally-Printed photographs - Part II," Int. Conf. Digital Printing Technol., pp. 664-669, 2004.
  3. M. Ebner, Color Constancy, Published in Association with the Society for IS&T, 2007.
  4. E. Y. Lam, "Combining gray world and retinex theory for automatic white balance in digital photography," in Proc. 9th Int. Symp. Consumer Electron., pp. 134-139, Jun. 2005.
  5. W.-R. Lee, D.-G. Hwang, and B.-M. Jun, "Analysis of color constancy methods for recovering skin color independent of illuminants," J. KICS, vol. 36, no. 10, pp. 621-628, 2011. https://doi.org/10.7840/KICS.2011.36C.10.621
  6. S.-H. Shin, Y.-S. Park, and Y.-S. Kim, "Adaptive video enhancement algorithm for military surveillance camera systems," J. KICS, vol. 39, no. 1, pp. 28-35, 2014. https://doi.org/10.7840/kics.2014.39C.1.28
  7. D. J. Jobson and G. A. Woodell, "Properties of a center/surround retinex: Part 2: Surround design," NASA Technical Memorandum 110188, pp. 15, 1995.
  8. L. Wang, T. Horiuchi, and H. Kotera, "High dynamic range image compression by fast integrated surround retinex model," J. Image Sci. Technol., vol. 51, no. 1, pp. 34-43, Jan.-Feb. 2007. https://doi.org/10.2352/J.ImagingSci.Technol.(2007)51:1(34)
  9. F. Dugay, L. Farup, and J. Y. Hardeberg, "Perceptual evaluation of color gamut mapping algorithms," Color Research and Appl., vol. 33, no. 6, pp. 470-476, 2008. https://doi.org/10.1002/col.20443
  10. J. Morovic, Color Gamut Mapping, Published in Association with the Society for IS&T, 2008.