Artificial Intelligence optimization For Low-Light Image Enhancement
Rosida Vivin Nahari, Mursidatul Hasanah, Eza Rahmanita, Riza Alfita, Miftachul Ulum · 2020
Image processing requires quality image data input to fulfill the desired final objective. Several pieces of research have been conducted in the effort to improve the image quality which is the initial process in the image processing to avoid poor output image quality. For example, a too dark image will make an unclear display of the image. The image occurs when shooting with low or dark lighting intensity. One of the ways to improve the image quality is by improving the contrast of the said image. This research is aimed to improve the image quality in the image by using the proposed method namely histogram equalization optimized using Particle Swarm optimization (PSO) algorithm to handle excessive image contrast. Several testing scenarios are conducted in this research to find out how optimal the influence of the PSO algorithm in the optimization process of improving image quality by handling excessive image contrast using the ExDark dataset. The results of testing conducted by comparing the average value of PSNR from Histogram Equalization and Histogram Equalization methods with the application of the PSO algorithm have obtained an average for the Histogram Equalization method of the three channels. The conducted research results in the enhancement of image quality with bigger accuracy compared to the ordinary Histogram Equalization method.