Abstract
Image super resolution is a vital research topic in the field of computer vision. It aims to reconstruct high resolution images from low resolution images. Although the conventional image super resolution methods have achieved good performance and effect, there are still have some issues, e.g., the high-frequency details information is insufficient, and the reconstruction process will bring additional noise, and most basic interpolation techniques produce blurry results. To settle the problems mentioned above, we consider combining the deep learning method with the frequency domain fusion method. In this paper, a novel single image super resolution method based on SRFeat network and wavelet fusion is proposed. First, the training image is taken as the input of the backbone SRFeat network, then the generative adversarial network training is carried out. Then, the up-sampling is utilized to obtain the coarse super resolved image. Finally, the output image after the network training is combined with the up-sampling image of the low-resolution image by Wavelet fusion to obtain the final result. Without increasing the depth of the network and the redundant parameters, the proposed method can achieve better reconstruct result. The experimental results show that the proposed method can not only reduce the probability of image distortion, but recover the global information of the reconstructed image and remove the noise brought by the reconstruction process. The PSNR value of the proposed method is improved 0.3 dB, and the SSIM is improved 0.02.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Dong C, Loy CC, He K et al (2016) Image super resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B et al (2014) Generative adversarial nets. Neural Inf Process Syst 20:2672–2680
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. Adaptive computation and machine learning. MIT Press, London, pp 1–775
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1664–1673
Hu C, Zhan S, Wu C (2017) Image super resolution reconstruction based on depth feature learning. J Autom 43(5):814–821
Irani M, Peleg S (1990) Super resolution from image sequences. Int Conf Pattern Recog 2:115–120
Kim J, Lee JK, Lee KM (2016a) Deeply-recursive convolutional network for image super resolution. In: IEEE conference on computer vision and pattern recognition, pp 1637–1645
Kim J, Lee JK, Lee KM (2016b) Accurate image super resolution using very deep convolutional networks. In: IEEE conference on computer vision and pattern recognition, pp 1646–1654
Lai WS, Huang JB, Ahuja N et al (2017) Deep laplacian pyramid networks for fast and accurate super resolution. In: IEEE conference on computer vision and pattern recognition, pp 5835–5843
Ledig C, Theis L, Huszar F et al (2016) Photo-realistic single image super resolution using a generative adversarial network. In: IEEE conference on computer vision and pattern recognition, pp 105–114
Lim B, Son S, Kim H et al (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136–144
Lu H, Wang D, Li Y et al (2019) CONet: a cognitive ocean network. IEEE Wirel Commun 26(3):90–96
Nie R, He M, Cao J et al (2019) Pulse coupled neural network based MRI image enhancement using classical visual receptive field for smarter mobile healthcare. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-018-1098-3
Park SJ, Hyeongseok S, Sunghyun C, Ki-Sang H, Seungyong L (2018) SRFeat: single image super resolution with feature discrimination. Computer vision-ECCV. Springer, Cham, pp 455–471
Schultz RR, Stevenson RL (1996) Motion-compensated scan conversion of interlaced video sequences image and video. Int Soc Opt Photon 2666:107–119
Shi W, Caballero J, Huszár F et al (2016) Real-time single image and video super-resolution using an efficient subpixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1874–1883
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations, pp 1–14
Stark H, Olsen ET (1992) Projection-based image restoration. J Opt Soc Am 9(11):1914–1919
Tai Y, Yang J, Liu X (2017) Image super resolution via deep recursive residual network. IEEE computer vision and pattern recognition. In: IEEE conference on computer vision and pattern recognition, pp 2790–2798
Tsai RY, Huang TS (1984) Multiframei mage restoration and registration advances. Comput Vis Image Process 20:317–339
Xi C, Shu Z, Dong J et al (2018) Image denoising via deep network based on edge enhancement. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-018-1036-4
Xu X, Lu H, Song J et al (2019) Ternary adversarial networks with self-supervision for zero-shot cross-modal retrieval. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2019.2928180
Xu X, Wang T, Yang Y, Zuo L, Shen F, Shen HT (2020) Cross-modal attention with semantic consistence for image-text matching. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/tnnls.2020.2967597
Zeng K, Ding S (2017) Advances in image super resolution reconstruction. Comput Eng Appl 53(16):29–35
Zhang K, Gao X, Tao D et al (2012) Single image super-resolution with non-local means and steering kernel regression. IEEE Trans Image Process 21(11):4544–4556
Zhu S, Zeng B, Liu G et al (2015) Image interpolation based on non-local geometric similarities. In: IEEE international conference on multimedia and expo, pp 1–6
Zhou F, Yang W, Liao Q (2012) Interpolation-based image super resolution using multisurface fitting. IEEE Trans Image Process 21(7):3312–3318
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
Ma, C., Zhu, J., Li, Y. et al. Single image super resolution via wavelet transform fusion and SRFeat network. J Ambient Intell Human Comput 13, 5023–5031 (2022). https://doi.org/10.1007/s12652-020-02065-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02065-0