An Approach for Enhancement of Low Contrast Gray Scale Image Using Fuzzy Logic and Sigmoid Function

Contrast enhancement plays a pivotal role in image processing, particularly for improving the visual quality of images in various applications. This paper presents an approach for enhancing such images by employing a point processing with the combination of Gaussian membership function for fuzzification and sigmoid function for modification. First, the image is fuzzified using Gaussian membership functions to transform pixel intensities into fuzzy sets, allowing for a more robust representation of the image's underlying characteristics. This fuzzification process effectively captures the uncertainty associated with pixel values in low contrast regions. Subsequently, a sigmoid function is applied to the fuzzified image to modify the pixel intensities. Experimental results demonstrate the efficacy of the proposed method in enhancing low contrast images, as evidenced by significant improvements in visual quality and quantitative metrics such as peak signal-to-noise ratio (PSNR) and entropy. The proposed approach offers a promising solution for enhancing low contrast images across various applications, contributing to advancements in image processing and analysis.