An Empirical Approach For Optimising The Impact of A Preprocessor in A Transcoding Pipeline

Recently, a lot of low-light image enhancement methods have been proposed. However, these methods have some problems such as causing over enhancement in bright regions and/or high computational cost. in this study, we propose a new low-light image enhancement method to improve these problems. in the proposed method, the input pixels are represented by a convex combination of white, black, and pure color. Then, an equ-hue plane in RGB color space is represented as the triangle whose vertices correspond to white, black, and pure color. The visibility of low-light image is improved by applying a modified gamma transform to the combination coefficients on an equ-hue plane in RGB color space. The contrast of image is enhanced by smoothing the histogram of black coefficient with a gamma filter. in the experiments, the effectiveness of the proposed method is verified by the comparison with the state-of-the-art low-light image enhancement methods.