A Rule-Based Fuzzy Inference System for Adaptive Image Contrast Enhancement

Adaptive contrast enhancement (ACE) is a popular method for image contrast enhancement. In this method, enhancement is achieved by adding an amplified version of the high-frequency content of the image to its low-frequency content. The rationale behind that is supported by the fact that the human visual system is sensitive to discontinuities in images, which represent the high-frequency content of the image. Thus, emphasizing this content is expected to improve the perceived contrast. In this paper, a fuzzy ACE (FACE)-based enhancement method, FACE, is proposed. In this method, the contrast gain values are computed using a fuzzy inference system (FIS) whose parameters are entirely derived from the image local statistics. To the best of our knowledge, the computation of the ACE gain values using a FIS has never been addressed before. Experimental results have proved the capability of FACE in enhancing the image contrast with less noise amplification and overenhancement artifacts.