Adaptive Haze Removal Utilizing Guided Filter Infused Approximate DCP

Abstract

In this project, we present a hybrid approach combining Adaptive Dual Combination Processing (ADCP) and the Guided Filter to enhance image quality, especially for haze free image reconstruction. The proposed method is evaluated using two datasets, including publicly available ones from Kaggle, demonstrating its adaptability to various datasets with minimal modifications to the algorithm. The performance of the proposed method is quantitatively analyzed using two widely recognized metrics: Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Higher PSNR values indicate better image clarity, while SSIM values close to 1 represent a strong structural similarity between the reconstructed and original images. Experimental results show that our ADCP and Guided Filter combination significantly improves both PSNR and SSIM, resulting in better image quality restoration compared to traditional approaches.