Abstract
Single Image Super Resolution (SISR) aims to recover high-frequency details of an image from its low-resolution form. It is a highly challenging problem since low-resolution image is blur and contains noise. The application of SISR can be found in various fields, such as microscopic image analysis, medical imaging, security and surveillance imaging, biometric image identification, hyper spectral imaging and text image super-resolution. Convolutional Neural Networks (CNNs) are the most widely used technique for SISR. Most of the previous CNN-based SISR methods blindly increase the network depth to achieve good performance, leading to increased computational cost. They train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth images. U-SRN model is proposed for single-image super-resolution, consisting of a contracting path to capture context and a symmetric expanding path that enables precise localization. Per-pixel loss is replaced with perceptual loss, which gives visually pleasing results. Extensive experiments show that the U-SRN model performs excellently and can perform multi-scale tasks. The model is trained on the DIV2K dataset. It is a benchmark dataset in the field of super-resolution, which consists of 1,000 high-quality images. Set 5, Set 14, Urban 100, and BSD 100 are the benchmark super-resolution datasets used for testing. For the upscaling factor of 4, the average gains on PSNR, SSIM and IFC achieved by U-SRN using Urban 100 dataset are 0.24 dB, 0.0037 and 0.025 higher than the next best approach. The results indicate that U-SRN performs better as compared to other state-of-art methods in terms of PSNR, SSIM and IFC on all datasets. The other performance analysis criterion, such as PI (4.12), FSIM (0.971), and SRQC (0.954), indicate the superiority of the model. The network has limited number of parameters and performs fast execution.
Similar content being viewed by others
References
Cheng Y, Ling K, Lin Y (2023) Image super resolution via combination of two dimensional quaternion valued singular spectrum analysis based denoising, empirical mode decomposition based denoising and discrete cosine transform based denoising methods. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-14474-2
Iqbal M, Riaz MM, Ghafoor A (2021) Kernel estimation and optimization for image de-blurring using mask construction and super-resolution. Multimed Tools Appl 80:10361–10372
Srinivas G, Naga Srinivasu P, Srinivas Rao T, Ramesh C (2018) Harmonic and Contra-Harmonic Mean-Centric JPEG Compression for an Objective Image Quality Enhancement of Noisy Images. Smart Comput Inform Smart Innov, Syst Technol, Springer 78:143–152. https://doi.org/10.1007/978-981-10-5547-8_14
Naga Srinivasu P, Balas VE, Md. Norwawi N (2021). Performance Measurement of Various Hybridized Kernels for Noise Normalization and Enhancement in High-Resolution MR Images. Bio-inspired Neurocomputing. Stud Comput Intell Springer, Singapore, 903, pp.1-24. https://doi.org/10.1007/978-981-15-5495-7_1
Bisen D, Shukla R, Rajpoot N (2022) Responsive human-computer interaction model based on recognition of facial landmarks using machine learning algorithms. Multimed Tools Appl 81:18011–18031
Mishra J, Goyal S (2022) An effective automatic traffic sign classification and recognition deep convolutional networks. Multimed Tools Appl 81:18915–18934
Senalp FM, Orhan B, Ceylan M (2023) Cloud environment-based super resolution application for thermal images using the new approach TSRGAN+ model. Multimed Tools Appl 82:18483–18500
Chen Y, Phonevilay V, Tao J (2021) The face image super-resolution algorithm based on combined representation learning. Multimed Tools Appl 80:30839–30861
Yin J, Xu SH, Du YB (2023) Super resolution reconstruction of CT images based on multi-scale attention mechanism. Multimed Tools Appl 12(4):4165–4183
Dong C, Loy C, He K, Tang X (2016) Image Super-Resolution Using Deep Convolutional Networks. IEEE Trans. on Pattern Anal. and Machine. Intelligence 38(2):295–307
Kim J, Lee J, Lee K (2016) Accurate Image Super-Resolution Using Very Deep Convolutional Networks Proc. 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1646-1654
Kim J, Lee J, Lee K (2016) Deeply-Recursive Convolutional Network for Image Super-Resolution. Proc. 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1637-1645.
Mao X, Shen C, Yang Y (2016) Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Proc. Neural Information Process. System, pp. 2810–2818
Dong C, Loy C, Tang X (2016) Accelerating the super resolution convolutional neural network, Proc. European Conf. on Computer Vision, pp. 658-673
Shi W, Caballero J, Huszár F, Totz J, Aitken A, Bishop R, Rueckert D, Wang Z (2016) Real-Time Single Image and Video Super-Resolution using an Efficient Sub-Pixel Convolutional Neural Network. Proc. 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1874-1883
Tai Y, Yang J, Liu X (2017) Image Super-Resolution via Deep Recursive Residual Network. Proc. 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2790-2798
Ledig C, Theis L, Huszár F ,Caballero J (2017) Photo-Realistic Single Image Super-Resolution using a Generative Adversarial Network, IEEE Conf. on Computer Vision and Pattern Recognition, pp.105-114
Tong T, Li G, Liu X, Gao Q (2017) Image Super-Resolution using Dense Skip Connections. Proc. 2017 IEEE International Conf. on Computer Vision, pp. 4809-4817
Shocher A, Cohen N, Irani M (2017) Zero-shot super-resolution using deep internal learning. Proc. Computer Vision Pattern Recognition, pp. 3118-3126
Kim J, Choi J, Cheon M, Lee J (2018) RAM: Residual attention module for single image super-resolution. Proc. Computer Vision Pattern Recognition, pp. 886-895
Lai W, Huang J, Ahuja N, Yang M (2017) Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution. Proc. 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 5835-5843
Zhang Y, Li K., Wang L., Zhong B, Fu Y (2018) Image super resolution using very deep residual channel attention networks. Proc. Computer Vision Pattern Recognition, pp.294-310
Haris M, Shakhnarovich G, Ukita N (2018) Deep Back-Projection Networks for Super-Resolution, Proc. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1664-1673
Cheng Y, Ling BWK, Lin Y (2023) Image super resolution via combination of two dimensional quaternion valued singular spectrum analysis based denoising, empirical mode decomposition based denoising and discrete cosine transform based denoising methods. Multimed Tools Appl 8(11):1136–1148
Wang Z, Liu D, Yang J (2016) Deep Networks for Image Super-Resolution with Sparse Prior, International Conference on Computer Vision, pp.370-378
Shen P, Zhang L, Wang M (2021) Deeper super-resolution generative adversarial network with gradient penalty for sonar image enhancement. Multimed Tools Appl 80:28087–28107
Hu S, Wang G, Wang Y (2020) Accurate image super-resolution using dense connections and dimension reduction network. Multimed Tools Appl 79:1427–1443
Song Z, Zhao X, Jiang H (2021) Gradual deep residual network for super-resolution. Multimed Tools Appl 80:9765–9778
Lan R, Sun L, Liu Z, Lu H, Pang C, Luo X (2020) MADNet: A Fast and Lightweight Network for Single-Image Super Resolution. IEEE Trans. on Cybernetics 9(6):4587–4612
Te X, Zhang J (2023) Clothing classification using transfer learning with squeeze and excitation block. Multimed Tools Appl 82:2839–2856. https://doi.org/10.1007/s11042-022-13395-w
Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation, Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, Springer 9351. https://doi.org/10.1007/978-3-319-24574-4_28
Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. European Conference on Computer Vision, pp.1-18
Sajjadi MS, Scholkopf B, Hirsch M (2017) Enhancenet: Single image super-resolution through automated texture synthesis. International Conference on Computer Vision, pp.4491-4500
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. International Conference on learning representations, pp.1-14
Li J, Fang F, Mei K, Zhang G (2018) Multi-scale residual network for image super-resolution. Proc. Eur. Conf. Comput. Vis. (ECCV), pp. 517–532
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), pp. 1132–1140
Agustsson E, Timofte R (2017) NTIRE 2017 challenge on single image super-resolution: Dataset and study. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop (CVPRW), pp. 1110–1121
Bevilacqua M, Roumy A, Guillemot C, Morel MLA (2012) Low complexity single-image super-resolution based on nonnegative neighbor embedding. Proc. Brit. Mach. Vis. Conf., pp. 135–145
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. Proc. Int. Conf. Curves Surf., pp. 711–730
Arbeláez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898–916
Huang J B, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 5197–5206
Srinivasu P, JayaLakshmi G, Jhaveri R, Praveen S (2022) Ambient Assistive Living for Monitoring the Physical Activity of Diabetic Adults through Body Area Networks. Mobile Information Systems, pp.1-18. https://doi.org/10.1155/2022/3169927
Peng Y (2020) Super-resolution Reconstruction Using Multiconnection Deep Residual Network Combined an Improved Loss Function for Single-frame Image. Multimed Tools Appl 79:9351–9362. https://doi.org/10.1007/s11042-019-7544-1
Huang J (2020) Image super-resolution reconstruction based on generative adversarial network model with double discriminators. Multimed Tools Appl 79:29639–29662
Mittal A, Soundararajan R, Bovik AC (2013) Making a “completely blind” image quality analyzer. IEEE Signal Process Lett 20(3):209–212
Zhang L, Zhang L, Mou X, Zhang D (2011) FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process 20(8):2378–2386
Greeshma MS, Bindu VR (2020) Super-resolution Quality Criterion (SRQC): a super-resolution image quality assessment metric. Multimed Tools Appl 79:35125–35146
Venkata N, Kite T, Geisler W (2000) Image quality assessment based on a degradation model. IEEE Trans Image Process 9(11):636–650
Ma C, Yang CY, Yang X, Yang MH (2017) Learning a no-reference quality metric for single-image super-resolution. Comput Vis Image Underst 15(8):1–16
Acknowledgments
Authors would like to express their gratitude to the anonymous reviewers for their insightful and productive feedback.
Data availability
NA
Code availability
NA
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dixit, M., Yadav, R.N. U-SRN: Convolutional Neural network for single image super resolution. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-17379-2
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-023-17379-2