Abstract
To improve the issue of low-frequency and high-frequency components from feature maps being treated equally in existing image super-resolution reconstruction methods, the paper proposed an image super-resolution reconstruction method using attention mechanism with feature map to facilitate reconstruction from original low-resolution images to multi-scale super-resolution images. The proposed model consists of a feature extraction block, an information extraction block, and a reconstruction module. Firstly, the extraction block is used to extract useful features from low-resolution images, with multiple information extraction blocks being combined with the feature map attention mechanism and passed between feature channels. Secondly, the interdependence is used to adaptively adjust the channel characteristics to restore more details. Finally, the reconstruction module reforms different scales high-resolution images. The experimental results can demonstrate that the proposed method can effectively improve not only the visual effect of images but also the results on the Set5, Set14, Urban100, and Manga109. The results can demonstrate the proposed method has structurally similarity to the image reconstruction methods. Furthermore, the evaluating indicator of Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM) has been improved to a certain degree, while the effectiveness of using feature map attention mechanism in image super-resolution reconstruction applications is useful and effective.
Similar content being viewed by others
References
Zhang L, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process 15(8):2226–2238
Chen YT, Tao JJ, Liu LW, Xiong J, Xia RL, Xie JB, Zhang Q, Yang K (2020) Research of improving semantic image segmentation based on a feature fusion model. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02066-z
Chen YT, Wang J, Liu SJ, Chen X, Xiong J, Xie JB, Yang K (2019) The multi-scale fast correlation filtering tracking algorithm based on a features fusion model. Concurrency Computat Pract Exper. https://doi.org/10.1002/cpe.5533
Yang J, Wright J, Huang TS, Yu L (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Timofte R, De Smet V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution. Paper presented at: Proceedings of the 2013 IEEE conference on computer vision (ICCV), Sydney, Australia, pp 1920–1927
Dong C, Loy CC, He KM, Tang XO (2014) Learning a deep convolutional network for image super-resolution. Paper presented at: Proceedings of the European conference on computer vision (ECCV), Zurich, Switzerland, pp 184–199
Kim J, Kwon Lee J, Mu Lee K (2016) Accurate image super-resolution using very deep convolutional networks. Paper presented at: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 1646–1654
He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. Paper presented at: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 770–778
Chen YT, Xiong J, Xu WH, Zuo JW (2019) A novel online incremental and decremental learning algorithm based on variable support vector machine. Cluster Comput 22(3):7435–7445
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. Paper presented at: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition workshops (CVPR workshops), Honolulu, pp 1132–1140
Tai Y, Yang J, Liu XM (2017) Image super-resolution via deep recursive residual network. Paper presented at: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, pp 2790–2798
Chen YT, Zhang HP, Liu LW, Tao JJ, Zhang Q, Yang K, Xia RL, Xie JB (2020) The image inpainting algorithm of texture decomposition and local variation minimization. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02778-2
Zhang H, Wang XM, Gao XB (2018) Fast and accurate single image super-resolution via information distillation network. Paper presented at: Proceedings of the 2018 IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, pp 723–731
Sakai Y, Lu HM, Tan J-K, Kim H (2019) Recognition of surrounding environment from electric wheelchair videos based on modified YOLOv2. Futur Gener Comput Syst 92:157–161
Memisevic R, Konda KR, Krueger D (2015) Zero-bias autoencoders and the benefits of co-adapting features. Paper presented at: Proceedings of the 2015 International Conference on Learning Representations (ICLR), San Diego, CA, USA arXiv:1402.3337
Xiang LY, Yang SH, Liu YH, Li Q, Zhu CZ (2020) Novel linguistic steganography based on character-level text generation. Mathematics. 8:1558
Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. Paper presented at: Proceedings of the 2010 International conference on machine learning (ICML), Haifa, pp 807–814
Chen YT, Liu LW, Tao JJ, Xia RL, Zhang Q, Yang K, Xiong J, Chen X (2020) The improved image inpainting algorithm via encoder and similarity constraint. Vis Comput. https://doi.org/10.1007/s00371-020-01932-3
Chen YT, Wang J, Chen X, Sangaiah AK, Yang K, Cao ZH (2019) Image super-resolution algorithm based on dual-channel convolutional neural networks. Appl Sci 9(11):2316
Sun L, Ma C, Chen Y, Zheng Y, Shim HJ, Wu Z, Jeon B (2019) Low rank component induced spatial-spectral kernel method for hyperspectral image classification. IEEE Trans Circ Syst Video T 30:3829–3842. https://doi.org/10.1109/TCSVT.2019.2946723
Chen YT, Liu LW, Tao JJ, Chen X, Xia RL, Zhang Q, Xiong J, Yang K, Xie JB (2020) The image annotation algorithm using convolutional features from intermediate layer of deep learning. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-09887-2
He SM, Li ZZ, Wang J, Xiong NX (2020) Intelligent detection for key performance indicators in industrial-based cyber-physical systems. IEEE Trans Ind Inform:1. https://doi.org/10.1109/TII.2020.3036168
Lu WP, Zhang YT, Wang SJ, Huang HY, Liu Q, Luo S (2020) Concept representation by learning explicit and implicit concept couplings. IEEE Intell Syst. https://doi.org/10.1109/MIS.2020.3021188
Martin D, Fowlkes C, Tal D, Malik J (2002) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Paper presented at: Proceedings of the 2002 International conference on computer vision (ICCV), Vancouver, pp 416–423
Chen YT, Zhang HP, Liu LW, Chen X, Zhang Q, Yang K, Xia RL, Xie JB (2020) Research on image inpainting algorithm of improved GAN based on two-discriminations networks. Appl Intell. https://doi.org/10.1007/s10489-020-01971-2
Chen YT, Phonevilay V, Tao JJ, Chen X, Xia RL, Zhang Q, Yang K, Xiong J, Xie JB (2020) The face image super-resolution algorithm based on combined representation learning. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-09969-1
Shi WZ, Caballero J, Huszar F, Totz J, Altken AP, Bishop R, Rueckert D, Wang ZH (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Paper presented at: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 1874–1883
Luo X, Tu XM, Ding Y, Gao G, Deng MH (2019) Expectation pooling: an effective and interpretable pooling method for predicting DNA–protein binding. Bioinformatics. https://doi.org/10.1093/bioinformatics/btz768
Timofte R, Agustsson E, Van Gool L, Yang MH, Zhang L, Lim B, Son S, Kim H, Nah S, Lee KM et al (2017) Ntire 2017 challenge on single image super-resolution: methods and results. Paper presented at: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition workshops (CVPR workshops), Honolulu, pp 1110–1121
Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. Paper Presented at: Proceedings of the 2015 IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, pp 3791–3799
Zhang JM, Sun J, Wang J, Yue XG (2020) Visual object tracking based on residual network and cascaded correlation filters. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02572-0
Kim J, Kwon Lee J, Mu Lee K (2016) Deeply-recursive convolutional network for image super-resolution. Paper presented at: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 1637–1645
Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, Aizawa K et al (2017) Sketch-based manga retrieval using manga109 dataset. Multimed Tools Appl 76(20):21811–21838
Soh JW, Cho S, Cho NI (2020) Meta-transfer learning for zero-shot super-resolution. Paper presented at: Proceedings of the 2020 IEEE conference on computer vision and pattern recognition (CVPR), Seattle, pp 3513–3522
Dai T, Cai JR, Zhang YB, Xia ST, Zhang L (2019) Second-order attention network for single image super-resolution. Paper presented at: Proceedings of the 2019 IEEE conference on computer vision and pattern recognition (CVPR), Long Beach, pp 11065–11074
Guo Y, Chen J, Wang JD, Chen Q, Cao JZ, Deng ZS, Xu YW, Tan MK (2020) Closed-loop matters: dual regression networks for single image super-resolution. Paper presented at: Proceedings of the 2020 IEEE conference on computer vision and pattern recognition (CVPR), Seattle, pp 5406–5415
Li F, Cong RM, Bai HH, He YF (2020) Deep interleaved network for single image super-resolution with asymmetric co-attention. Paper presented at: proceedings of the twenty-ninth international joint conference on artificial intelligence (IJCAI), Yokohama, Japan, pp 537–543
Liu J, Zhang WJ, Tang YT, Tang J, Wu GS (2020) Residual feature aggregation network for image super-resolution. Paper presented at: Proceedings of the 2020 IEEE conference on computer vision and pattern recognition (CVPR), Seattle, pp 2356–2365
Sheikh HR, Sabir MF, Bovik AC (2006) A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans Image Process 15(11):3440–3451
Acknowledgements
This work is supported by the National Natural Science Foundation of China [61972056, 61772454, 61402053, 61981340416], the Natural Science Foundation of Hunan Province of China [2020JJ4623], the Scientific Research Fund of Hunan Provincial Education Department [17A007, 19C0028, 19B005], the Junior Faculty Development Program Project of Changsha University of Science and Technology [2019QJCZ011], the “Double First-class” International Cooperation and Development Scientific Research Project of Changsha University of Science and Technology [2019IC34], the Practical Innovation and Entrepreneurship Ability Improvement Plan for Professional Degree Postgraduate of Changsha University of Science and Technology [SJCX202072], the Postgraduate Training Innovation Base Construction Project of Hunan Province [2019-248-51, 2020-172-48].
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
Chen, Y., Liu, L., Phonevilay, V. et al. Image super-resolution reconstruction based on feature map attention mechanism. Appl Intell 51, 4367–4380 (2021). https://doi.org/10.1007/s10489-020-02116-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-02116-1