The Research on a New Image Enhancement Algorithm Based on Retinex Theory

Abstract

On the basis of Retinex theory, We know that SSR (SSR, Single Scale Retinex) algorithms mainly consists of two steps: estimation and normalization of illumination. The illumination is estimated as a smooth version of input image using gaussian low-pass filters. In this paper, We propose a method to improve SSR algorithm. We used Butterworth low-pass filter instead of gaussian low-pass filter to smooth the image, Compared with traditional Retinex algorithm, The experimental results shows that, The result images using modified SSR algorithm have greater entropy and average gradient.