Autoregressive Models and Non-Local Self Similarity in Sparse Representation for Image Deblurring
Y Ravi Sankaraiah1, S Varadarajan2
1Y Ravi Sankaraiah, Research Scholar, Department of Engineering and Communication Engineering, JNTUK, Kakinada, India.
2S. Varadarajan, Professor, Department of Engineering and Communication Engineering, Sri Venkateswara University, Tirupati, India.
Manuscript received on 26 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 443-449 | Volume-8 Issue-9, July 2019 | Retrieval Number: I7786078919/19©BEIESP | DOI: 10.35940/ijitee.I7786.078919
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Local area within a normal natural image can be thought as a stationary process. This can be modelled well using autoregressive models. In this paper, a set of autoregressive models will be learned from a collection of high quality image patches. Out of these models, one will be selected adaptively and will be used to regularize the input image patches. In addition to the autoregressive models, a non-local self-similarity condition was proposed. The autoregressive models will exploit local correlation of individual image, but a natural will have many repetitive structures. These structures, which are basically redundant, are very much useful in image deblurring. The performance of these schemes is verified by applying to image deblurring.
Index Terms: Autoregressive Models, Deblurring, Non-Local Self-Similarity, Sparse Domain Selection.
Scope of the Article: Knowledge Representation and Retrievals