Rain Streaks Removal in digital images by Dictionary based sparsity process with MCA Estimation

Abstract

During the rainy season, many public outdoor crimes have been caught through video surveillance, and they do not have complete feature information to identify the image features. Rain streak removal techniques are ideal for indexing and obtaining additional information from such images. Furthermore, the rain substantially changes the intensity of images and videos, lowering the overall image quality of vision systems in outdoor recording situations. To be successful, the elimination of rain streaks in the film will require an advanced trial and error method. Different methods have been utilized to identify and eliminate the rainy effects by using the data on photon numbers, chromaticity, and probability of rain streaks present in digital images. This research work includes sparse coding process for removing rain streak by incorporating morphological component analyses (MCA) based algorithm. Based on the MCA algorithm, the coarse estimation becomes very simple to handle the rain streak or impulsive noisy images. The sparse decomposition of coarse is possible by estimating and eliminating all redundancies from the sources. This novel MCA approach is combined with sparsity coding process to provide better PSNR and less MSE results from the reconstructed images. This method is compared with of the existing research works on rain streak removal process. Besides, the obtained the results are illustrated and tabulated.