An Efficient Image Contrast Enhancement Algorithm Using Genetic Algorithm and Fuzzy Intensification Operator

• Published in: Wireless personal communications 2017-03, Vol.93 (1), p.223-244
• Main Authors: Surya Prabha, D., Satheesh Kumar, J.
• Format: Article
• Language: English
• Subjects: Communications Engineering; Computer Communication Networks; Computer vision; Engineering; Equalization; Genetic algorithms; Histograms; Image contrast; Image enhancement; Image manipulation; Image processing; Networks; Noise measurement; Parameterization; Quantitative analysis; Signal to noise ratio; Signal,Image and Speech Processing; Similarity; Variance analysis
• ISSN: 0929-6212; 1572-834X
• DOI: 10.1007/s11277-016-3536-x

Image contrast enhancement algorithms play a crucial role in image processing and computer vision. The main challenge in contrast enhancement is that an algorithm suitable for low contrast distorted images does not suit for high contrast distorted images. In this paper, an efficient contrast enhancement algorithm with automated parameterization is proposed using the concept of genetic algorithm and fuzzy intensification operator. Main focus of the proposed method is to improve the visibility information of an image by manipulating their intensity information. Simulation results of the proposed fuzzy-genetic based method were compared with standard existing methods such as log, gamma, linear contrast stretching, histogram equalization, adaptive histogram equalization and rule based fuzzy method using their default parameter values. Performance of the proposed and existing methods on very low, low, moderate, high and very high levels of contrast distorted images were quantitatively measured using peak signal to noise ratio (PSNR), structural similarity index measure (SSIM) and feature similarity index measure (FSIM). The PSNR, SSIM and FSIM values were statistically analysed by two-way ANOVA. Results of this experiment inferred that (a) the contrast enhancement techniques performed well when the level of distortions were very low to moderate, (b) contrast enhancement was better in the proposed fuzzy-genetic based method than other existing methods, and (c) overall, the proposed fuzzy-genetic based method performed well on very low to very high levels of distorted images with higher PSNR, SSIM and FSIM values than other existing methods.