Analysis of conventional and modern contrast enhancement mechanisms.

Contrast enhancement is a crucial aspect of image processing, as it improves visual quality by adjusting the brightness and contrast of an image. This paper comprehensively explores contrast enhancement techniques, classified into three categories: Image Processing (IP) based methods Deep Learning (DL) based approaches, and Generative Adversarial Network (GAN) methods. The paper also details various quality evaluation methods for enhanced images and compares different algorithms. The performance of the presented algorithms is evaluated using metrics such as Structural Similarity Index Measurement (SSIM), Absolute Mean Brightness Error (AMBE), Average Information Content (AIC), Contrast Improvement Index (CII), Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Universal Quality Index (UQI), and Color Enhancement Factor (CEF). The comparative analysis aims to provide insights into improving image quality, information content and error production within each category, facilitating informed decision-making in selecting contrast enhancement techniques for diverse applications. [ABSTRACT FROM AUTHOR]