Example-based color alternation for images

Abstract

This paper presents an example-based color alternation algorithm between images. Dissimilar to a well-known conventional color transfer method, our approach takes into consideration the weighted influences of the source as well as the target image. Our algorithm automatically calculates the weights according to a fuzzy value, either derived from the statistical features of the source and target images, or adjusted by the users. As a result, our algorithm produces more natural, attractive, and versatile results. Our algorithm has five advantages. First, it is a general approach where the conventional method is a special case of our method. Second, it guarantees the success of color alternation, not always possible for using the conventional color transfer method. Third, the quality of the outcome images is more visually plausible than our counterparts'. Fourth, it is simple and efficient. It does not need to generate swatches, and results can be processed within seconds. Finally, it can produce more varied, versatile results that can be controlled by the users.