Bregman-Tanimoto Based Method for Contrast Preserving Decolorization

This paper presents a novel Bregman-Tanimoto based model for faithfully contrast-preserving decolorization. With regard to the defects of the traditional Euclidean metric approaches, the proposed method addresses the problems by introducing a Bregman-Tanimoto metric based maximum function, thus more details, features and visual distinctiveness can be preserved. Moreover, the model extends the solution space of the first-order linear parameter model used for color-to-gray mapping. An extended discrete searching algorithm is developed to solve the proposed model. Experimental results show that the proposed approach outperforms other state-of-the-art methods both quantitatively and qualitatively.