Preserving Maximum Color Contrast in Generation of Gray Images

Author: Alex Yong-Sang Chia, Keita Yaegashi and Soh Masuko


We propose a method to preserve maximum color contrast when converting a color image to its gray representation. Specifically, we aim to preserve color contrast in the color image as gray contrast in the gray image. Given a color image, we first extract unique colors of the image through robust clustering for its color values. We tailor a non-linear decolorization function that preserves the maximum contrast in the gray image on the basis of the color contrast between the unique colors. A key contribution of our method is the proposal of a color-gray feature that tightly couples color contrast information with gray contrast information. We compute the optimal color-gray feature, and focus the search for a decolorization function on generating a color-gray feature that is most similar to the optimal one. This decolorization function is then used to convert the color image to its gray representation. Our experiments and a user study demonstrate the superior performance of this method in comparison with current state-of-the-art techniques.

Keywords: Image processing · Image decolorization · Feature represen- tation · Coarse-to-fine search

Copied! instagram
Research Areas : #Vision Program
Careers : Open Positions