Efficient learning based Image Super Resolution via Sparse Representation

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

Prediction of Two StageAir Compressor Characteristic

The paper reports investigation of indicating power input, the poly topic compression index and overall efficiency of two stage air compressor under condition of atmospheric pressure and temperature in Shuwaikh Kuwait. T...

EmpiricalAnalysis of Document Similarity Using Statistical Model

Information retrieval is great technology behind web search services. This paper presents the statistical method for content based information. Mainly three paradigms of models are used in retrieving information. These a...

Using a Case Based Organizational Memory for Recommendation Systems

With the aim to manage and retrieve the organizational knowledge, in the last years numerous proposals of models and tools for knowledge management and knowledge representation have arisen. However, most of them store kn...

Invitro Evaluation of Antimicrobial Activity of the plant extracts of Elytraria acaulis

Antimicrobial activity of the aerial parts of the Elytraria acaulis a stem less perennial herb of Acantheceae family has been carried out in the present study. Extracts of the aerial parts of the plant (Stem & Leaves) we...

Segmentation and Identification of Indian food items from Images

Now people are interested in food analysis with advanced technologies in many areas. In this paper we proposed a food identification system for South Indian food images. The system is based on segmenting the food images...

Download PDF file
  • EP ID EP392014
  • DOI 10.9790/9622-0708033949.
  • Views 102
  • Downloads 0

How To Cite

R. Sudheer Babu, Dr. K. E. Sreenivasa Murthy (2017). Efficient learning based Image Super Resolution via Sparse Representation. International Journal of engineering Research and Applications, 7(8), 39-49. https://europub.co.uk/articles/-A-392014