Different environmental illumination has a great impact on face detection and recognition. Automatic detection and radiant correction of highlighted region on face image is helpful to identify human faces correctly in a color image. In this paper we present a novel approach based on dichromatic reflection model to detect and remove highlight in face region. After inspecting the distribution configuration of skin pixels in various color models, we perform the highlight analysis on a critical two-dimensional plane instead of in a three-dimensional chromatic space. This brings forth some advantages: computational complexity is deduced, a ratio between eigenvalues is proposed in a stepwise PCA to detect automatically the existence of highlighted face region and estimate the skin dichromatic reflection vectors, by which highlight in face region can be removed.