Texture and edge preserving multiframe super‐resolution. Issue 9 (1st September 2014)

• Record Type: Journal Article
• Authors: Turgay, Emre; Akar, Gozde B.
• Is Part Of: IET image processing. Volume 8:Issue 9(2014)
• Page Start: 499
• Page End: 508
• Publication Date: 2014-09-01
• Subjects: discrete cosine transforms -- Gabor filters -- image reconstruction -- image resolution -- image texture -- maximum likelihood estimation; super resolution image reconstruction -- overlapping aliased low‐resolution observation -- edge preservation -- SR literature -- texture‐speciflc regularisation -- two stage method -- multiple SR reconstruction -- regularisation parameters -- restoration step -- maximum‐a‐posteriori estimators -- pixel‐to‐pixel difference -- texture preserving multiframe super resolution -- edge preserving multiframe super resolution -- frequency selective characteristics -- discrete cosine transform -- Gabor fllters -- post‐processing step; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2013.0342
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Super‐resolution (SR) image reconstruction refers to methods where a higher resolution image is reconstructed using a set of overlapping aliased low‐resolution observations of the same scene. Although edge preservation has been a widely explored topic in SR literature, texture‐specific regularisation has recently gained interest. In this study, texture‐specific regularisation is handled as a post‐processing step. A two stage method is proposed, comprising multiple SR reconstructions with different regularisation parameters followed by a restoration step for preserving edges and textures. In the first stage, two maximum‐a‐posteriori estimators with two different amounts of regularisation are employed. In the second stage, pixel‐to‐pixel difference between these two estimates is post‐processed to restore edges and textures. Frequency selective characteristics of discrete cosine transform and Gabor filters are utilised in the post‐processing step. Experiments on synthetically generated images and real experiments demonstrate that the proposed methods give better results compared with the state‐of‐the‐art SR methods especially on textures and edges.