Saliency preserving decolorization

This paper presents a new decolorization approach using saliency including color and position information to maintain original contrast. Our approach includes three steps: (1) we propose a visual contrast model which quantifies saliency via pixel based contrast along with area based contrast, using both color difference and spatial relationship, (2) we put forward an energy function with the purpose of minimizing the gap between color image and corresponding grayscale's saliency, where grayscale is represented by a mapping function of color channels, (3) we accelerate the calculation of energy function by loosening or strengthening constraint. Experimental results on public benchmark images show that the use of saliency can preserve the contrast of the original color image better than state of the art decolorization methods.