PROJECT TITLE :

Sequence-to-Sequence Similarity-Based Filter for Image Denoising

ABSTRACT:

Image denoising has been a well-studied problem for imaging systems, particularly imaging sensors. Despite outstanding progress in the standard of denoising algorithms, persistent challenges remain for a large category of general pictures. In this paper, we tend to present a replacement concept of sequence-to-sequence similarity (SSS). This similarity measure is an economical method to guage the content similarity for images, particularly for edge data. The approach differs from the ancient image processing techniques, that depend on pixel and block similarity. Primarily based on this new concept, we tend to introduce a brand new SSS-based mostly filter for image denoising. The new SSS-based mostly filter utilizes the edge information within the corrupted image to handle image denoising problems. We tend to demonstrate the filter by incorporating it into a brand new SSS-based image denoising algorithm to get rid of Gaussian noise. Experiments are performed over artificial and experimental knowledge. The performance of our methodology is experimentally verified on a variety of images and Gaussian noise levels. The results demonstrate that the proposed method’s performance exceeds many current state-of-the-art works, which are evaluated each visually and quantitatively. The presented framework opens up new views in the utilization of SSS methodologies for image processing applications to exchange the ancient pixel-to-pixel similarity or block-to-block similarity.