{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T05:34:54Z","timestamp":1761197694657,"version":"3.41.2"},"reference-count":23,"publisher":"Emerald","issue":"3","license":[{"start":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T00:00:00Z","timestamp":1565568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emeraldinsight.com\/page\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJICC"],"published-print":{"date-parts":[[2019,8,12]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>Conventional image super-resolution reconstruction by the conventional deep learning architectures suffers from the problems of hard training and gradient disappearing. In order to solve such problems, the purpose of this paper is to propose a novel image super-resolution algorithm based on improved generative adversarial networks (GANs) with Wasserstein distance and gradient penalty.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>The proposed algorithm first introduces the conventional GANs architecture, the Wasserstein distance and the gradient penalty for the task of image super-resolution reconstruction (SRWGANs-GP). In addition, a novel perceptual loss function is designed for the SRWGANs-GP to meet the task of image super-resolution reconstruction. The content loss is extracted from the deep model\u2019s feature maps, and such features are introduced to calculate mean square error (MSE) for the loss calculation of generators.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>To validate the effectiveness and feasibility of the proposed algorithm, a lot of compared experiments are applied on three common data sets, i.e. Set5, Set14 and BSD100. Experimental results have shown that the proposed SRWGANs-GP architecture has a stable error gradient and iteratively convergence. Compared with the baseline deep models, the proposed GANs models have a significant improvement on performance and efficiency for image super-resolution reconstruction. The MSE calculated by the deep model\u2019s feature maps gives more advantages for constructing contour and texture.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>Compared with the state-of-the-art algorithms, the proposed algorithm obtains a better performance on image super-resolution and better reconstruction results on contour and texture.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ijicc-10-2018-0135","type":"journal-article","created":{"date-parts":[[2019,8,16]],"date-time":"2019-08-16T03:19:49Z","timestamp":1565925589000},"page":"400-413","source":"Crossref","is-referenced-by-count":9,"title":["A novel image super-resolution reconstruction algorithm based on improved GANs and gradient penalty"],"prefix":"10.1108","volume":"12","author":[{"given":"Shuangshuang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","reference":[{"first-page":"58","article-title":"Hybrid super-resolution combining example-based single-image and interpolation-based multi-image reconstruction approaches","year":"2015","key":"key2019081607194019100_ref001"},{"issue":"2","key":"key2019081607194019100_ref002","first-page":"1","article-title":"Low-complexity single-image super-resolution based on nonnegative neighbor embedding","volume":"12","year":"2012"},{"issue":"7586","key":"key2019081607194019100_ref003","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1038\/nature16496","article-title":"Super-resolution imaging reveals distinct chromatin folding for different epigenetic states","volume":"529","year":"2016","journal-title":"Nature"},{"first-page":"391","article-title":"Accelerating the super-resolution convolutional neural network","year":"2016","key":"key2019081607194019100_ref004"},{"first-page":"2672","article-title":"Generative adversarial nets","year":"2014","key":"key2019081607194019100_ref005"},{"first-page":"770","article-title":"Deep residual learning for image recognition","year":"2016","key":"key2019081607194019100_ref006"},{"first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","year":"2016","key":"key2019081607194019100_ref007"},{"first-page":"1646","article-title":"Accurate image super-resolution using very deep convolutional networks","year":"2016","key":"key2019081607194019100_ref008"},{"first-page":"1637","article-title":"Deeply-recursive convolutional network for image super-resolution","year":"2016","key":"key2019081607194019100_ref009"},{"first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","year":"2012","key":"key2019081607194019100_ref010"},{"first-page":"4681","article-title":"Photo-realistic single image super-resolution using a generative adversarial network","year":"2017","key":"key2019081607194019100_ref011"},{"first-page":"291","article-title":"Computed tomography image enhancement using 3D convolutional neural network","year":"2018","key":"key2019081607194019100_ref012"},{"issue":"1","key":"key2019081607194019100_ref013","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1186\/s12859-018-2365-1","article-title":"Exploring spatial-frequency-sequential relationships for motor imagery classification with recurrent neural network","volume":"19","year":"2018","journal-title":"BMC Bioinformatics"},{"first-page":"697","article-title":"Deep reinforcement learning from error-related potentials via an EEG-based brain-computer interface","year":"2018","key":"key2019081607194019100_ref014"},{"key":"key2019081607194019100_ref015","doi-asserted-by":"crossref","first-page":"219","DOI":"10.3389\/fnins.2018.00219","article-title":"Effect of different movement speed modes on human action observation: an EEG study","volume":"12","year":"2018","journal-title":"Frontiers in Neuroscience"},{"first-page":"1825","article-title":"The numerics of gans","year":"2017","key":"key2019081607194019100_ref016"},{"first-page":"1874","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","year":"2016","key":"key2019081607194019100_ref017"},{"issue":"12","key":"key2019081607194019100_ref018","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1016\/j.tcb.2015.10.004","article-title":"Super-resolution microscopy: from single molecules to supramolecular assemblies","volume":"25","year":"2015","journal-title":"Trends in Cell Biology"},{"first-page":"1865","article-title":"Seven ways to improve example-based single image super-resolution","year":"2016","key":"key2019081607194019100_ref019"},{"first-page":"616","article-title":"Learning to learn: model regression networks for easy small sample learning","year":"2016","key":"key2019081607194019100_ref020"},{"year":"2017","key":"key2019081607194019100_ref021","article-title":"Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN)"},{"issue":"8","key":"key2019081607194019100_ref022","doi-asserted-by":"crossref","first-page":"4862","DOI":"10.1021\/acs.nanolett.6b01255","article-title":"Super-resolution imaging of a dielectric microsphere is governed by the waist of its photonic nanojet","volume":"16","year":"2016","journal-title":"Nano Letters"},{"issue":"1","key":"key2019081607194019100_ref023","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1504\/IJCSE.2017.10002203","article-title":"A GPU-based statistical image up-sampling method by using edge templates","volume":"14","year":"2017","journal-title":"International Journal of Computational Science and Engineering"}],"container-title":["International Journal of Intelligent Computing and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emeraldinsight.com\/doi\/full-xml\/10.1108\/IJICC-10-2018-0135","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emeraldinsight.com\/doi\/full\/10.1108\/IJICC-10-2018-0135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:54:58Z","timestamp":1753397698000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijicc\/article\/12\/3\/400-413\/119970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,12]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,8,12]]}},"alternative-id":["10.1108\/IJICC-10-2018-0135"],"URL":"https:\/\/doi.org\/10.1108\/ijicc-10-2018-0135","relation":{},"ISSN":["1756-378X"],"issn-type":[{"type":"print","value":"1756-378X"}],"subject":[],"published":{"date-parts":[[2019,8,12]]}}}