Naturalness balance contrast enhancement using adaptive gamma with cumulative histogram and median filtering

Abstract

In the domain of contrast enhancement, contrast as well as detail retention are critical for human visualization and onward processing by any other computer based application. Contrast enhancement of an image with naturalness and preserved details is a challenge. In this paper, we propose a method using an edge-preserving smoothing operator approach, based on the weighted least squares (WLS) optimization. The detail and base layers are extracted using the WLS and median filters respectively. Base layer is a smooth layer of the image that contains large scale intensity changes and the detail layer captures the smaller scale details in the image. The layers are enhanced with a fine tuning between the rate of enhancement of the base and detail layers. It is vital to manage the level of enhancement in both the extracted layers as any mistune in the rate of enhancement may lead to severe distortion and addition of artifacts. Color correction is applied to the image to provide a higher-resolution improved image. The simulation results over 680 images from different datasets, show that the proposed method outperforms the existing methods in terms of qualitative and quantitative parameters.