Efficient learning based Image Super Resolution via Sparse Representation
Journal Title: International Journal of engineering Research and Applications - Year 2017, Vol 7, Issue 8
Abstract
This paper addresses the problem of generating a superresolution (SR) image from a single low-resolution input image. Research on image statistics suggests that image patches can be well represented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary. Inspired by this observation, we seek a sparse representation for each patch of the low-resolution input, and then use the coefficients of this representation to generate the high-resolution output. By jointly training two dictionaries for the low- and highresolution image patches, we can enforce the similarity of sparse representations between the low resolution and high resolution image patch pair with respect to their own dictionaries. Therefore, the sparse representation of a low resolution image patch can be applied with the high resolution image patch dictionary to generate a high resolution image patch. The learned dictionary pair is a more compact representation of the patch pairs, compared to previous approaches, which simply sample a large amount of image patch pairs [1], reducing the computational cost substantially. The effectiveness of such sparsity prior is demonstrated for general image superresolution. In this case, our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. In addition, the local sparse modeling of our approach is naturally robust to noise, and therefore the proposed algorithm can handle super-resolution with noisy inputs in a more unified framework.
Authors and Affiliations
R. Sudheer Babu, Dr. K. E. Sreenivasa Murthy
Keywords
Related Articles
- EP ID EP392014
- DOI 10.9790/9622-0708033949.
- Views 117
- Downloads 0
Non-Exhaustible Solar-Power Based Insecticide or Bio-fertilizer Sprayer for Use in Agronomics (With Bluetooth Enabled Control)
Agronomics is a profession of many related sequential and sometimes concurrent tedious processes and methodologies. The Primary process among many is the spraying of insecticides, pesticides, liquefied fertilizers in the...
Multi-Purpose Robot using Raspberry Pi & Controlled by Smartphone
This paper proposes a method for controlling a Wireless robot for multi-purpose in the sense surveillance, rescue operations and weather reporting, human detection, geo-graphical location etc., Generally surveillance rob...
Effect of Deposition Temperature on the Physical Properties of Ag-Cu2O Thin Films by D C Magnetron Sputtering
We report co-deposited Ag-Cu2O films using DC Magnetron Sputtering method on glass substrates. Both Ag content and temperature were varied during deposition. UV-VIS-NIR, Hall measurements were used to characterize the op...
A Review of Masonry Buckling Characteristics
Masonry load bearing wall subjected to vertical concentric and eccentric loading may collapse through instability. In this Paper the buckling behaviour of masonry load bearing wall of different slenderness ratio were inv...
Design of A High Speed And Low Power 4 Bit Carry Skip Adder
This paper focuses on carry skip adder (CSKA) structure that has a higher speed yet lower power consumption compared with the conventional one. The speed enhancement is achieved by applying Transmission gate logic (TG) t...