{"title":"Neural network based single image super resolution","authors":"N. Kumar, P. Deswal, J. Mehta, A. Sethi","doi":"10.1109/NEUREL.2012.6420014","DOIUrl":null,"url":null,"abstract":"In this paper a novel learning based technique for single image super resolution (SR) is proposed. We model the relationship between available low resolution (LR) image and desired high resolution (HR) image as multi-scale markov random field (MSMRF). We re-formulate the SR problem in terms of learning the mapping between LR-MRF and HR-MRF, which is generally non-linear. Instead of learning MSMRF parameters we use artificial neural networks to learn the desired mapping. The results compare favorably to more complex stat-of-the art techniques for 2 × 2 and 3 × 3 SR problem. We solve the SR problem using optical zoom as a cue by the proposed algorithm as well. The results on experiments with real data are presented.","PeriodicalId":343718,"journal":{"name":"11th Symposium on Neural Network Applications in Electrical Engineering","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"11th Symposium on Neural Network Applications in Electrical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NEUREL.2012.6420014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
In this paper a novel learning based technique for single image super resolution (SR) is proposed. We model the relationship between available low resolution (LR) image and desired high resolution (HR) image as multi-scale markov random field (MSMRF). We re-formulate the SR problem in terms of learning the mapping between LR-MRF and HR-MRF, which is generally non-linear. Instead of learning MSMRF parameters we use artificial neural networks to learn the desired mapping. The results compare favorably to more complex stat-of-the art techniques for 2 × 2 and 3 × 3 SR problem. We solve the SR problem using optical zoom as a cue by the proposed algorithm as well. The results on experiments with real data are presented.