Abstract
Aiming at insufficient detailed description problem caused by the loss of edges during a single low-resolution (LR) image’s reconstruction process, a novel algorithm for super resolution image reconstruction is proposed in this paper, which is based on fusion of internal structural self-similarity dictionary and external convolution neural network parameters learning model. Firstly, for solving training samples too scattered problem, besides external database, an internal database is constructed to learn a dictionary of the single image’s structural self-similarity by multi-scale decomposition approach. Secondly, nonlocal regularization constraint is calculated on the priori knowledge, which is obtained from the internal database of the single LR image. Thirdly, similar block pairs of high and low-resolution samples in the external database are input into a convolution neural network for learning the parameters of reconstructing model. After all, combined parameters learned and the internal dictionary, the single LR image is reconstructed, and by iterative back-projection algorithm its result is improved. Experimental results show that, compared with state-of-the-art algorithms, such as Bicubic, K-SVD algorithm and SRCNN algorithm, our method is more effective and efficient.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Atkins CB (1998) Classification-based methods in optimal image interpolation. Dissertation, Purdue University
Bu HH, Kim NC, Park KW (2019) Content-based image retrieval using combined texture and color features based on multi-resolution multi-direction filtering and color auto-corr-elogram. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-019-01466-0
Chang K, Ding PLK, Li BX (2018) Single image super resolution using joint regularization. IEEE Signal Process Lett 25(4):596–600
Chikhaoui B, Ye B, Mihailidis A (2017) Feature-level combination of skeleton joints and body parts for accurate aggressive and agitated behavior recognition. J Ambient Intell Humaniz Comput 8(6):957–976
Dai D, Timoft R, Vangool LV (2015) Jointly optimized regressors for image super-resolution. Comput Graph Forum 34(2):95–104
Dai Y, Jin T, Song Y (2019) SRCNN-based enhanced imaging for low frequency radar. 2018 Progress in Electromagnetics Research Symposium. https://doi.org/10.23919/PIERS.2018.8597817
Dian R, Fang L, Li S (2017) Hyperspectral image super-resolution via non-local sparse tensor factorization. IEEE Conf Comput Vis Pattern Recogn. https://doi.org/10.1109/CVPR.2017.411
Eldib M, Deboeverie F, Philips W (2018) Discovering activity patterns in office environment using a network of low-resolution visual sensors. J Ambient Intell Humaniz Comput 9(2):381–411
Elsaid NMH, Wu YC (2019) Super-resolution diffusion tensor imaging using SRCNN: a feasibility study. 41st Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC): 2830–2834
He J, Zhang J, Zhang Y (2018) Image super-resolution reconstruction algorithm based on convolutional neural network. IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE).https://doi.org/10.1109/AUTEEE.2018.8720786
Hou S, Zhang F, Li X (2017) Simultaneous multi-component seismic denoising and reconstruction via K-SVD. J Geophys Eng 15(3):681–694
Hu J, Wu X, Zhou J (2018) Noise robust single image super-resolution using a multiscale image pyramid. Signal Process 148:157–171
Huo Z, Wu Z, Xu W (2019) Research on image super-resolution reconstruction method based on improved SRCNN. J Phys Conf Ser. https://doi.org/10.1088/1742-6596/1345/2/022008
Ismail S, Mansour H, Allam M (2014) Super resolution. reconstruction of high-resolution image from a set of low-resolution images. LAP LAMBERT Academic Publishing: 25–65
Ji Q, Zhang L (2018) Mental fatigue detection based on multi-inter-domain optical flow characteristics. 5th International Conference on Information Science and Control Engineering: 316–320
Kang Y, Kim YJ (2015) Super-resolution generalizing nonlocal means and kernel regression. arXiv. https://arxiv.org/abs/1503.04253
Li Z, He H, Wang R (2015) Single image super-resolution bidirectional group sparsity and directional features. Image Process 9(24):2874–2888
Liang M, Du J, Cao S (2015) Super-resolution reconstruction based on multisource bidirectional similarity and non-local similarity matching. IET Image Proc 9(11):931–942
Luo W, Liu J, Huang Y (2020) An effective vitiligo intelligent classification system. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02357-5
Ma C, Zhu J, Li Y (2020) Single image super resolution via wavelet transform fusion and SRFeat network. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02065-0
Ruqia B, Zahid M, Rehan M (2020) Query-by- visual-search: multimodal framework for content based image retrieval. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-01923-1
Saraswathi S, Madheswaran M (2020) Adaptive supervised multi-resolution approach-based modeling of performance improvement in satellite image classification. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02251-0
Shi W, Caballero J, Huszár F(2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 1874–1883
Tong T, Li G, Liu X (2017) Image super-resolution using dense skip connections. IEEE International Conference on Computer Vision (ICCV). 4809–4817
Wang H, Lu F, Li J (2016) Single image super-resolution via support vector regression and image self-similarity. J Image Graph 21(8):986–992
Watchara R, Supavadee A (2017) Efficient super-resolution algorithm using overlapping bicubic interpolation. 6th global conference on consumer electronics. https://doi.org/10.1109/GCCE.2017.8229459
Xu J, Zhang L, Zuo W (2015) Patch group based nonlocal self-similarity prior learning for image denoising. IEEE Int Conf Comput Vis (ICCV) 1:244–252
Xu J, Shen Z, Tian Z (2018) GPR data reconstruction method based on compressive sensing and K-SVD. Near Surf Geophys 16(1):13–21
You XG, Xue WY (2016) Single image super-resolution with non-local balanced low-rank matrix restoration. Int Conf Pattern Recognit (ICPR) 10(23):1255–1260
Zeng J, Ni L (2019) Improved super-resolution reconstruction of single image based on convolution neural network. Comput Eng Appl 55(13):1–7
Zhu Z (2018) Research on compressive sensing image super resolution reconstruction using SRCNN. Dissertation, Harbin Engineering University
Acknowledgements
This paper is funded by Scientific Project of Guangdong Provincial Transport Department (No. Sci & Tec-2016-02-30), Natural Science Foundation of Guangdong Province under Grant 2018A030313061, in part by the Guangdong Science and Technology Plan under Grant 2017B010124001, Grant 201902020016, and Grant 2019B010139001, in part by Anhui Provincial Natural Science Foundation under Grant 2008085J01.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, L., Jiang, W. & Xiang, W. Dictionary learning based on structural self-similarity and convolution neural network. J Ambient Intell Human Comput 13, 1463–1470 (2022). https://doi.org/10.1007/s12652-020-02739-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02739-9