Research on color correction algorithm for mobile-end tongue images

Shadows and chromatic aberration problems are existed in the mobile tongue images, which result in tongue images obtained from the mobile devices cannot be directly used for auxiliary diagnosis. To better acquire the color features of the tongue images, we analyze the HIT tongue database and our mobile tongue dataset. Comparing to the HIT tongue database, we found insufficient exposure might be the root cause of above problems in the mobile tongue dataset. Therefore, we propose a two-stage color correction algorithm to effectively solve two problems. To remove the shadows in the tongue images, Frankle-McCann retinex algorithm is implemented. Then, to restore the whole color distribution of the tongue images as real world, the gray world algorithm is utilized to fine-tune the color values of the tongue images. Qualitative and quantitative analysis show that the proposed algorithm can achieve good objective and real visual results.