Directive local color transfer based on dynamic look-up table

Highlights：

• We study several open image datasets and propose a novel color mapping method based on the human vision system, which is more accurate and reasonable than the existed methods.

• A novel method for abstracting salient regions is proposed based on the improved simple non-iterative clustering (I-SNIC) method. This method can detect salient regions more accurate and outperforms the classic method. Furthermore, the I-SNIC method fits boundaries better than the simple non-iterative clustering (SNIC) method especially for the color transfer.

• Dynamic color look-up tables are established to enrich the colors of the reference image and to prevent the appearance of the pseudo contour region.

• This paper provides a manual interaction method, which is convenient, friendly and fast to use. Furthermore, we also extend the range of the reference image, which the color blocks can also be added to the reference images.