Microscopic Images Improvement Depending on Dark Channel Prior and Adaptive Histogram Equalization based on the Lab Colour Model

Optical microscopes face limitations due to diffraction, which can impact the clarity and resolution of the resulting images. Enhancing these images typically involves techniques such as contrast improvement, sharpening, and noise reduction, which help make features more discernible. In this study, we propose an algorithm aimed at enhancing contrast and illumination using Dark Channel Prior (DCP) and Adaptive Histogram Equalization (AHE) to improve image clarity. For illumination enhancement, we utilize the Lab color model, specifically focusing on the light formation component (L) while preserving color. This method was compared against several others, including the Retinex Algorithm with Colour Restoration, Adaptive Histogram Equalization and Fuzzy Logic, Fuzzy Logic by Stretch Membership Function, Median-Mean Based Sub-Image-Clipped Histogram Equalization, Principal Component Analysis Using Reflection Model, and Modified Color Histogram Equalization, using both reference and non-reference quality standards. Our algorithm aims to enhance image contrast and brightness without introducing color distortion, achieving favorable values for Entropy (7.913), mean of the standard deviation (61.04), Structural Similarity Index Metric (0.760), and Perception-based Image Quality Evaluator (35.324).