2021/07/10 by Basit Alawode, Basit O. Alawode, Alawode, Basit O. +7
Computer Science · Engineering · Mathematics · #Advanced Image Fusion Techniques #Advanced Image Processing Techniques #Algorithm #Artificial intelligence #Computer science #Computer vision #Domain (mathematical analysis) #FOS: Electrical engineering #Image (mathematics) #Image Processing Techniques and Applications #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Image denoising #Mathematics #Noise (video) #Noise reduction #Non-local means #Pattern recognition (psychology) #Photoacoustic and Ultrasonic Imaging #Signal Processing (eess.SP) #Video denoising #eess.IV #eess.SP #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2107.04865
arxiv created 2021/07/10 · openalex publication_date 2021/07/10 · arxiv updated 2021/07/13 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Over the years, progressive improvements in denoising performance have been\nachieved by several image denoising algorithms that have been proposed. Despite\nthis, many of these state-of-the-art algorithms tend to smooth out the denoised\nimage resulting in the loss of some image details after denoising. Many also\ndistort images of lower resolution resulting in a partial or complete\nstructural loss. In this paper, we address these shortcomings by proposing a\ncollaborative filtering-based (CoFiB) denoising algorithm. Our proposed\nalgorithm performs weighted sparse domain collaborative denoising by taking\nadvantage of the fact that similar patches tend to have similar sparse\nrepresentations in the sparse domain. This gives our algorithm the intelligence\nto strike a balance between image detail preservation and noise removal. Our\nextensive experiments showed that our proposed CoFiB algorithm does not only\npreserve the image details but also perform excellently for images of any given\nresolution where many denoising algorithms tend to struggle, specifically at\nlow resolutions.\n