Faded Color Correction using Classification Map in LCybCrg Color Space

LCybCrg 색 공간에서 분류맵을 이용한 바랜 색 보정

  • Kyung, Wang-Jun (School of Electronics Engineering, Kyungpook National University) ;
  • Kim, Dae-Chul (School of Electronics Engineering, Kyungpook National University) ;
  • Lee, Cheol-Hee (Computer Engineering, Andong National University) ;
  • Ha, Yeong-Ho (School of Electronics Engineering, Kyungpook National University)
  • Received : 2011.11.01
  • Accepted : 2012.01.31
  • Published : 2012.03.25

Abstract

Generally, correction methods for faded images use illuminant estimation algorithms, such as the gray world assumption and white patch Retinex methods, as the phenomenon of color fading is regarded as an illuminant effect. However, this induces inaccurate faded color correction, as images fade at different rates according to the ink property, temperature, humidity, and illuminant. Therefore, this paper presents a color correction method for faded images using classification in LCybCrg color space. The input faded image is first separated according to the chromaticity based on LCybCrg opponent color space. The faded color correction is then performed based on the gray world assumption in RGB color space. Thereafter, weights calculated from CybCrg values are applied to reduce contour artifacts. As a result, the proposed method provides better color correction for faded images than previous methods.

일반적으로 바랜 영상 보정 방법들은 색 바램의 현상은 광원의 효과로서, Gray World Assumption 또는 White Patch Retinex와 같은 광원 추정 알고리즘을 사용한다. 그러나 이러한 방법들은 염료의 특성, 온도, 습도, 광원 등에 따라 다르게 바래는 색에 대한 보정은 부정확함을 나타냈다. 본 논문에서는 LCybCrg 색 공간에서의 분류맵을 이용한 바랜 색 보정 방법을 제안한다. 먼저 입력의 색 바랜 영상은 LCybCrg의 보색 공간의 색도를 기반으로 하여 분류되었다. 그리고 RGB 색 공간에서 Gray World Assumption을 기반으로 하여 바랜 색도를 보정하였다. 또한 CybCrg 값으로부터 계산된 가중치는 각각의 영역에서 발생 할 수 있는 윤곽효과를 줄이기 위해 적용되었다. 그 결과 제안한 방법은 바랜 영상에 대해 이전 방법들 보다 더 나은 보정 성능을 보였다.

Keywords

References

  1. Franziska S. Frey, Rudolf Gschwind, and Lukas Rosenthaler, "Electronic Imaging, a Tool for the Reconstruction of Faded Color Photographs and Motion Pictures," The Fourth Color Imaging Conference, pp. 39-44, 1996.
  2. Henry Wilhelm, "A Review of Accelerated Test Methods for Predicting the Image Life of Digitally-Printed Photographs - Part II," International Conference on Digital Printing Technologies, pp. 664-669, 2004.
  3. Marc Ebner, "Color Constancy," Published in Association with the Society for IS&T, 2007.
  4. Edmund Y. Lam, "Combining Gray World and Retinex Theory for Automatic White Balance in Digital Photography," Proceedings of the 9th International Symposium on Consumer Electronics, pp. 134-139., 2005.
  5. J. Morovic, "Color Gamut Mapping," Published in Association with the Society for IS&T, 2008.
  6. Margarita Bratkova, Solomon Boulos, and Peter Shirley, "oRGB: A Practical Opponent Color Space for Computer Graphics," IEEE Computer Graphics and Applications, vol. 29, no. 1, pp. 42-55, 2009. https://doi.org/10.1109/MCG.2009.13
  7. Fabienne Duay, Lvar Farup, Jon Y. Hardeberg, "Perceptual Evaluation of Color Gamut Mapping Algorithms," Color Research and Application, vol. 33, no. 6, pp. 470-476, 2008. https://doi.org/10.1002/col.20443