Preventing Over-Enhancement Using Modified ICSO Algorithm

Abstract

This paper proposes an Image Contrast Enhancement (ICE) method based on using an Improved Chicken Swarm Optimization (ICSO) algorithm to enhance images while at the same time preventing over-enhancement. In the optimization process, a new practical objective function is employed to reach three main goals, preserving the main details, generating an image with a uniform histogram, and reducing the spikes in the modified histogram. In the proposed approach, the RGB color channels are optimized individually. The performance of the proposed method is suitable for enhancing the contrast of low-and high-contrast images. A subjective experiment is designed to visually evaluate and compare the results with other ICE methods. The simulation results on the CSIQ, TID2013, and SEID datasets show that the proposed method outperforms numerous traditional and state-of-the-art ICE techniques both subjectively and objectively. The most important advantage of the newly proposed technique is that there is an agreement among observers on when over-enhancement occurs regardless of whether the Initial processed image was of low or high contrast. INDEX TERMSContrast enhancement, image quality assessment, over-enhancement.

Individual Contrast Preferences in Natural Images

“…Cherepkova et al [15] show that observers have distinguishable patterns with regard to contrast distortion when judging image quality, where some observers rate images with higher contrast to have higher quality and vice versa. Contrast is a fundamental image attribute that can influence how the image is perceived by observers and has a significant impact on IQA [16] and enhancement [17]. The effect of contrast on perceived image quality was discovered in early works; an example of such a subjective experiment was reported in the work of Roufs and Goossens in 1988 [13] and by Roufs et al in 1994 [18].…”