Color correction of faded images using multi-scale gray world algorithm

Wang-Jun Kyung, Dae-Chul Kim, Massimo Fierro, Yeong-Ho Ha
Kyungpook National University (South Korea)
Download paper

Play (12min)

Download: MP4 | MP3

The enhancement of faded color on old pictures, printings, and paintings is one of important issue in color image processing. Several techniques have been introduced to enhance the faded images. Almost techniques are performed with global illuminant estimation algorithms such as the gray world assumption and white patch Retinex methods, since the phenomenon of color fading is regarded as an illuminant effect. However, fading effect is shown up differently according to the ink property, temperature, humidity, illuminants, and so on. Therefore simple global operators to eliminate the illuminant effects are not suitable for enhancing faded images. This paper presents a color enhancement algorithm based on multi-scale gray world algorithm for faded images. First, the proposed method adopts local process by using multi-scale mask. The coefficients for each multi-scale 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.