Stroke width‐based directional total variation regularisation for document image super resolution. Issue 2 (1st February 2016)

• Record Type: Journal Article
• Authors: Abedi, Ali; Kabir, Ehsanollah
• Is Part Of: IET image processing. Volume 10:Issue 2(2016)
• Page Start: 158
• Page End: 166
• Publication Date: 2016-02-01
• Subjects: image resolution -- document image processing -- Bayes methods -- variational techniques -- smoothing methods -- edge detection -- interpolation -- data encapsulation -- image reconstruction; stroke width‐based directional total variation regularisation -- document image super resolution -- Bayesian image super resolution -- bilateral total variation -- BTV -- uniform image smoothing -- edge preservation -- document image SR method -- LR image analysis -- interpolation -- local direction -- local width -- SWDTV regularisation -- information encapsulation -- HR image reconstruction -- visual image quality improvement; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2014.1021
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : In the Bayesian image super resolution (SR), a regularisation term is minimised along with a data‐fidelity term to generate a high‐resolution (HR) image from input low‐resolution (LR) image. The regularisation term is incorporated into the SR to fulfil a prior knowledge over the HR image. For instance, smoothness in the background and foreground regions is a prior knowledge about document images. The bilateral total variation (BTV), as a known regularisation term, uniformly smooths the image in all directions while preserving the edges. In this study, the authors present a document image SR method by introducing a new regularisation term called the stroke width‐based directional total variation (SWDTV). It is a modified version of the BTV, and adaptively performs smoothing based on the local width and local direction of the character strokes. By analysing the input LR image and its interpolation, the local stroke width and local stroke direction in the output image are approximated. This information is encapsulated into the SWDTV regularisation term. By minimising the linear combination of the regularisation and data‐fidelity terms, the HR image is reconstructed. The authors' method achieves significant improvements in visual image quality and optical character recognition accuracy compared to related non‐example‐based document image SR methods.