Image Enhancement Using Successive Mean Quantization Transform and Homomorphic Filtering

Abstract

Low contrast images are not conducive to human perception and computer vision algorithms due to their low discernibility. In many application quality of acquired images are not suitable, so image has to be enhanced according to the need of a specific application. To solve the problems of detail loss, poor contrast and problems of noise, a new technique based on homomorphic filtering is proposed. This paper contributes to combine the filter based and Successive Mean Quantization Transform (SMQT) algorithm for better image quality of digital image by minimizing the properties such as gain and bias. First, we investigate the result for the standard images and experimental images. Second, we measure the results by using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), blind/reference less image spatial quality evaluator (BRISQUE) and Blind Image Quality Indices (BIQI). Finally, model is compared with enhancement algorithms. Simulation and experimental results demonstrates that proposed model provides better results as compared to other state-of-art contrast enhancement algorithms. The implementation is done using MATLAB.