Adaptive switching interpolation filter for restoring impulse corrupted digital images. Issue 12 (4th September 2020)

• Record Type: Journal Article
• Authors: Varghese, Justin; Subash, Saudia; Sridhar, Kuttaiyur Palaniswamy; Balaji, Narayanasamy Venkattaramanujam; Ashok Kumar, Gopalakrishnan
• Is Part Of: IET image processing. Volume 14:Issue 12(2020)
• Page Start: 2869
• Page End: 2878
• Publication Date: 2020-09-04
• Subjects: computational geometry -- median filters -- adaptive filters -- image denoising -- image enhancement -- image representation -- extrapolation -- image restoration -- impulse noise -- interpolation; impulse corrupted digital images -- adaptive switching interpolation filter -- interpolation scheme -- Shepard's inverse distance -- Simpson's natural neighbour interpolation techniques -- uncorrupted pixels -- natural neighbour‐based techniques -- interpolation methods -- natural intensity variations -- image enhancement factor -- comparative filters -- salt & pepper impulse noise; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.1445
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : The study introduces an adaptive switching interpolation filter (ASIF) for restoring images contaminated with salt & pepper impulse noise. The new method restores noisy pixels by applying a new interpolation scheme that combines Shepard's inverse distance weighting and Simpson's natural neighbour interpolation techniques. The new interpolation scheme is designed based on the percentage of the overlapping area and the distance between the sites created by noisy pixels with the sites of uncorrupted pixels in the Voronoi tessellation. Since natural neighbour‐based techniques do not support extrapolation, the proposed algorithm performs Shepard's inverse distance weighting‐based restoration when the noisy pixels fall outside the convex hull formed by uncorrupted pixels. As the proposed method combines the advantages of Simpson's natural neighbour and Shepard's inverse distance weighting interpolation methods, it better preserves the natural intensity variations in images and provides smoother approximation than other methods used in the comparative study. Visual and quantitative experimental analysis performed on various images with peak signal to noise ratio, mean structural similarity index measure, image enhancement factor, and feature‐similarity index measure demarcates the improved capability of ASIF over other comparative filters.