{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:49:52Z","timestamp":1740145792606,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005408","name":"University of Electronic Science and Technology of China","doi-asserted-by":"publisher","award":["ZYGX2017KYQD157"],"award-info":[{"award-number":["ZYGX2017KYQD157"]}],"id":[{"id":"10.13039\/501100005408","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Image Video Proc."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we propose a hybrid super-resolution method by combining global and local dictionary training in the sparse domain. In order to present and differentiate the feature mapping in different scales, a global dictionary set is trained in multiple structure scales, and a non-linear function is used to choose the appropriate dictionary to initially reconstruct the HR image. In addition, we introduce the Gaussian blur to the LR images to eliminate a widely used but inappropriate assumption that the low resolution (LR) images are generated by bicubic interpolation from high-resolution (HR) images. In order to deal with Gaussian blur, a local dictionary is generated and iteratively updated by <jats:italic>K<\/jats:italic>-means principal component analysis (K-PCA) and gradient decent (GD) to model the blur effect during the down-sampling. Compared with the state-of-the-art SR algorithms, the experimental results reveal that the proposed method can produce sharper boundaries and suppress undesired artifacts with the present of Gaussian blur. It implies that our method could be more effect in real applications and that the HR-LR mapping relation is more complicated than bicubic interpolation.<\/jats:p>","DOI":"10.1186\/s13640-021-00552-8","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T08:02:40Z","timestamp":1621238560000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Single image super resolution based on multi-scale structure and non-local smoothing"],"prefix":"10.1186","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1619-0294","authenticated-orcid":false,"given":"Wenyi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jun","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jiying","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jianwen","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,17]]},"reference":[{"key":"552_CR1","volume-title":"Advances in computer vision and image processing","author":"R. Y. Tsai","year":"1984","unstructured":"R. Y. Tsai, T. S. Huang, Advances in computer vision and image processing (JAI Press, Greenwich, CT, USA, 1984)."},{"issue":"6","key":"552_CR2","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TIP.2004.826093","volume":"13","author":"T. Blu","year":"2004","unstructured":"T. Blu, P. Thevenaz, M. Unser, Linear interpolation revitalized. IEEE Trans. Image Process.13(6), 710\u2013719 (2004).","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"552_CR3","doi-asserted-by":"publisher","first-page":"1521","DOI":"10.1109\/83.951537","volume":"10","author":"X. Li","year":"2001","unstructured":"X. Li, M. Orchard, New edge-directed interpolation. IEEE Trans. Image Process.10(10), 1521\u20131527 (2001).","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"552_CR4","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TIP.2006.877407","volume":"15","author":"L. Zhang","year":"2006","unstructured":"L. Zhang, X. Wu, An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans. Image Process.15(8), 2226\u20132238 (2006).","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"552_CR5","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1109\/TIP.2010.2095871","volume":"20","author":"J. Sun","year":"2011","unstructured":"J. Sun, Z. Xu, H. Shum, Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Trans. Image Process.20(6), 1529\u20131542 (2011).","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"552_CR6","doi-asserted-by":"publisher","first-page":"4544","DOI":"10.1109\/TIP.2012.2208977","volume":"21","author":"K. Zhang","year":"2012","unstructured":"K. Zhang, X. Gao, D. Tao, X. Li, Single image super-resolution with nonlocal means and steering kernel regression. IEEE Trans. Image Process.21(11), 4544\u20134556 (2012).","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"552_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/38.988747","volume":"22","author":"W. Freeman","year":"2002","unstructured":"W. Freeman, T. Jones, E. Pasztor, Example-based super-resolution. IEEE Comput. Graph. Appl. Mag.22(2), 56\u201365 (2002).","journal-title":"IEEE Comput. Graph. Appl. Mag."},{"issue":"6","key":"552_CR8","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1109\/TIP.2007.896644","volume":"16","author":"K. Ni","year":"2007","unstructured":"K. Ni, T. Nguyen, Image super-resolution using support vector regression. IEEE Trans. Image Process.16(6), 1596\u20131610 (2007).","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"552_CR9","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.1109\/TIP.2010.2050625","volume":"19","author":"J. Yang","year":"2010","unstructured":"J. Yang, J. Wright, T. S. Huang, Y. Ma, Image super-resolution via sparse representation. IEEE Trans. Image Process.19(11), 2861\u20132873 (2010).","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"552_CR10","doi-asserted-by":"publisher","first-page":"3467","DOI":"10.1109\/TIP.2012.2192127","volume":"21","author":"J. Yang","year":"2012","unstructured":"J. Yang, Z. Wang, Z. Lin, S. Cohen, T. Huang, Coupled dictionary training for image super-resolution. IEEE Trans. Image Process.21(8), 3467\u20133478 (2012).","journal-title":"IEEE Trans. Image Process."},{"key":"552_CR11","doi-asserted-by":"crossref","unstructured":"R. Zeyde, M. Elad, M. Protter, in Proceedings of 8th International Conference: Curves and Surfaces. On single image scale-up using sparse-representations, pp. 711\u2013730 (2010).","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"552_CR12","doi-asserted-by":"crossref","unstructured":"R. Timofte, V. D. Smet, L. V. Gool, in Proceedings of IEEE International Conference on Computer Vision. Anchored neighborhood regression for fast example-based super-resolution, pp. 1920\u20131927 (2013).","DOI":"10.1109\/ICCV.2013.241"},{"key":"552_CR13","doi-asserted-by":"crossref","unstructured":"R. Timofte, V. D. Smet, L. V. Gool, in Proceedings of Asian Conference on Computer Vision. Adjusted anchored neighborhood regression for fast super-resolution, pp. 111\u2013126 (2014).","DOI":"10.1007\/978-3-319-16817-3_8"},{"issue":"34","key":"552_CR14","first-page":"1","volume":"2018","author":"W. Shi","year":"2018","unstructured":"W. Shi, S. Liu, F. Jiang, D. Zhao, Z. Tian, Anchored neighborhood deep network for single-image super-resolution. EURASIP J. Image Video Process.2018(34), 1\u201312 (2018).","journal-title":"EURASIP J. Image Video Process."},{"issue":"10","key":"552_CR15","doi-asserted-by":"publisher","first-page":"4701","DOI":"10.1109\/TIT.2009.2027565","volume":"55","author":"M. Elad","year":"2009","unstructured":"M. Elad, I. Yavneh, A plurality of sparse representations is better than the sparsest one alone. IEEE Trans. Inf. Theory. 55(10), 4701\u20134714 (2009).","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"7","key":"552_CR16","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1109\/TIP.2011.2108306","volume":"20","author":"W. Dong","year":"2011","unstructured":"W. Dong, L. Zhang, G. Shi, X. Wu, Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans. Image Process.20(7), 1838\u20131857 (2011).","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"552_CR17","doi-asserted-by":"publisher","first-page":"1620","DOI":"10.1109\/TIP.2012.2235847","volume":"22","author":"W. Dong","year":"2013","unstructured":"W. Dong, L. Zhang, G. Shi, X. Li, Nonlocally centralized sparse representation for image restoration. IEEE Trans. Image Process.22(4), 1620\u20131630 (2013).","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"552_CR18","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1109\/TIP.2015.2389629","volume":"24","author":"K. Zhang","year":"2015","unstructured":"K. Zhang, D. Tao, X. Gao, X. Li, Z. Xiong, Learning multiple linear mappings for efficient single image super-resolution. IEEE Trans. Image Process.24(3), 846\u2013861 (2015).","journal-title":"IEEE Trans. Image Process."},{"key":"552_CR19","doi-asserted-by":"crossref","unstructured":"C. Dong, C. C. Loy, K. He, X. Tang, in Proceedings of European Conference on Computer Vision. Learning a deep convolutional network for image super-resolution, pp. 184\u2013199 (2014).","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"552_CR20","doi-asserted-by":"crossref","unstructured":"J. Kim, J. K. Lee, K. M. Lee, in IEEE Conference on Computer Vision and Pattern Recognition. Accurate image superresolution using very deep convolutional networks, (2016).","DOI":"10.1109\/CVPR.2016.182"},{"key":"552_CR21","doi-asserted-by":"crossref","unstructured":"J. Hu, J. Zhao, in Proceedings of IEEE International Conference on Instrumentation and Measurement Technology. A joint dictionary based method for single image super-resolution, pp. 1440\u20131444 (2016).","DOI":"10.1109\/I2MTC.2016.7520581"},{"issue":"3","key":"552_CR22","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s10915-008-9214-8","volume":"37","author":"A. Marquina","year":"2008","unstructured":"A. Marquina, S. J. Osher, Image super-resolution by tv-regularization and bregman iteration. J. Sci. Comput.37(3), 367\u2013382 (2008).","journal-title":"J. Sci. Comput."},{"issue":"10","key":"552_CR23","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.1109\/TIP.2005.851684","volume":"14","author":"H. A. Aly","year":"2005","unstructured":"H. A. Aly, E. Dubois, Image up-sampling using total-variation regularization with a new observation model. IEEE Trans. Image Process.14(10), 1647\u20131659 (2005).","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"552_CR24","doi-asserted-by":"publisher","first-page":"511","DOI":"10.3934\/ipi.2011.5.511","volume":"5","author":"G. Peyre","year":"2011","unstructured":"G. Peyre, S. Bougleux, L. Cohen, Non-local regularization of inverse problems. Inverse Probl. Imaging. 5(2), 511\u2013530 (2011).","journal-title":"Inverse Probl. Imaging"},{"issue":"11","key":"552_CR25","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1002\/cpa.20042","volume":"57","author":"I. Daubechies","year":"2004","unstructured":"I. Daubechies, M. Defrise, C. D. Mol, An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pur. Appl. Math.57(11), 1413\u20131457 (2004).","journal-title":"Commun. Pur. Appl. Math."},{"issue":"6","key":"552_CR26","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1109\/JPROC.2010.2044010","volume":"98","author":"J. A. Troopp","year":"2010","unstructured":"J. A. Troopp, S. J. Wright, Computational methods for sparse solution of linear inverse problems. Proc. IEEE. 98(6), 948\u2013958 (2010).","journal-title":"Proc. IEEE"},{"issue":"6","key":"552_CR27","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1109\/TPAMI.2010.25","volume":"32","author":"K. I. Kim","year":"2010","unstructured":"K. I. Kim, Y. Kwon, Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell.32(6), 1127\u20131133 (2010).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"552_CR28","doi-asserted-by":"publisher","first-page":"2797","DOI":"10.1109\/TIP.2015.2431435","volume":"24","author":"Y. Zhang","year":"2015","unstructured":"Y. Zhang, W. Yang, Z. Guo, Image super-resolution based on structure-modulated sparse representation. IEEE Trans. Image Process.24(9), 2797\u20132810 (2015).","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"552_CR29","doi-asserted-by":"publisher","first-page":"2797","DOI":"10.1109\/TIP.2015.2431435","volume":"24","author":"Y. Zhang","year":"2015","unstructured":"Y. Zhang, J. Liu, W. Yang, Z. Guo, Image super-resolution based on structure-modulated sparse representation. IEEE Trans. Image Process.24(9), 2797\u20132810 (2015).","journal-title":"IEEE Trans. Image Process."},{"issue":"5-6","key":"552_CR30","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/s00041-008-9045-x","volume":"14","author":"E. Cand\u00e9s","year":"2008","unstructured":"E. Cand\u00e9s, Enhancing sparsity by reweighted l1 minimization. J. Fourier Anal. Appl.14(5-6), 877\u2013905 (2008).","journal-title":"J. Fourier Anal. Appl."},{"key":"552_CR31","doi-asserted-by":"crossref","unstructured":"M. Bevilacqua, A. Roumy, C. Guillemot, M. -L. Alberi-Morel, in Proceedings of BMVC. Low complexity single-image super-resolution based on nonnegative neighbor embedding, pp. 135\u2013113510 (2012).","DOI":"10.5244\/C.26.135"}],"container-title":["EURASIP Journal on Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-021-00552-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13640-021-00552-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-021-00552-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T08:09:04Z","timestamp":1621238944000},"score":1,"resource":{"primary":{"URL":"https:\/\/jivp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13640-021-00552-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,17]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["552"],"URL":"https:\/\/doi.org\/10.1186\/s13640-021-00552-8","relation":{},"ISSN":["1687-5281"],"issn-type":[{"type":"electronic","value":"1687-5281"}],"subject":[],"published":{"date-parts":[[2021,5,17]]},"assertion":[{"value":"8 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"16"}}