[KSCI] Korea Science Citation Index Service

http://dx.doi.org/10.22937/IJCSNS.2021.21.12.63

LDCSIR: Lightweight Deep CNN-based Approach for Single Image Super-Resolution

Muhammad, Wazir (Department of Electrical Engineering, Balochistan University of Engineering & Technology)
Shaikh, Murtaza Hussain (Department of Information Systems, Kyungsung University)
Shah, Jalal (Department of Computer Systems Engineering, Balochistan University of Engineering & Technology)
Shah, Syed Ali Raza (Department of Mechanical Engineering, Balochistan University of Engineering & Technology)
Bhutto, Zuhaibuddin (Department of Computer Systems Engineering, Balochistan University of Engineering & Technology)
Lehri, Liaquat Ali (Department of Mechanical Engineering, Balochistan University of Engineering & Technology)
Hussain, Ayaz (Department of Electrical Engineering, Balochistan University of Engineering & Technology)
Masrour, Salman (Department of Mechanical Engineering, Balochistan University of Engineering & Technology)
Ali, Shamshad (Department of Electrical Engineering, Balochistan University of Engineering & Technology)
Thaheem, Imdadullah (Department of Energy System Engineering, Balochistan University of Engineering & Technology)

Publication Information

International Journal of Computer Science & Network Security / v.21, no.12spc, 2021 , pp. 463-468 More about this Journal

Abstract

Single image super-resolution (SISR) is an image processing technique, and its main target is to reconstruct the high-quality or high-resolution (HR) image from the low-quality or low-resolution (LR) image. Currently, deep learning-based convolutional neural network (CNN) image super-resolution approaches achieved remarkable improvement over the previous approaches. Furthermore, earlier approaches used hand designed filter to upscale the LR image into HR image. The design architecture of such approaches is easy, but it introduces the extra unwanted pixels in the reconstructed image. To resolve these issues, we propose novel deep learning-based approach known as Lightweight deep CNN-based approach for Single Image Super-Resolution (LDCSIR). In this paper, we propose a new architecture which is inspired by ResNet with Inception blocks, which significantly drop the computational cost of the model and increase the processing time for reconstructing the HR image. Compared with the other state of the art methods, LDCSIR achieves better performance in terms of quantitively (PSNR/SSIM) and qualitatively.

Keywords

Image super-resolution; Convolutional neural network; PSNR; ResNet block;

Citations & Related Records

Reference

1	Krizhevsky, A., I. Sutskever, and G.E. Hinton. Imagenet classification with deep convolutional neural networks. in Advances in neural information processing systems. 2012.
2	Yang, C.-Y., C. Ma, and M.-H. Yang. Single-image super-resolution: A benchmark. in European conference on computer vision. 2014. Springer.
3	Ledig, C., et al. Photo-realistic single image super-resolution using a generative adversarial network. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
4	Dong, C., C.C. Loy, and X. Tang. Accelerating the super-resolution convolutional neural network. in European conference on computer vision. 2016. Springer.
5	Lai, W.-S., et al. Deep laplacian pyramid networks for fast and accurate super-resolution. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
6	Zhang, K., et al. Learning deep CNN denoiser prior for image restoration. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
7	Muhammad, W. and S.J.E. Aramvith, Multi-Scale Inception Based Super-Resolution Using Deep Learning Approach. 2019. 8(8): p. 892. DOI
8	Lin, M., Q. Chen, and S. Yan, Network in network. arXiv preprint arXiv:1312.4400, 2013.
9	Bevilacqua, M., et al., Low-complexity single-image super-resolution based on nonnegative neighbor embedding. 2012.
10	Dong, C., et al., Image super-resolution using deep convolutional networks. 2015. 38(2): p. 295-307.
11	Zhang, K., W. Zuo, and L. Zhang. Learning a single convolutional super-resolution network for multiple degradations. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
12	Kim, J., J. Kwon Lee, and K. Mu Lee. Accurate image super-resolution using very deep convolutional networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
13	Hsu, J.-T., C.-H. Kuo, and D.-W.J.I.A. Chen, Image Super-Resolution Using Capsule Neural Networks. 2020. 8: p. 9751-9759. DOI
14	Zeyde, R., M. Elad, and M. Protter. On single image scale-up using sparse-representations. in International conference on curves and surfaces. 2010. Springer.
15	Dong, C., et al., Image Super-Resolution Using Deep Convolutional Networks. 2016. 38(2): p. 295-307.
16	Nair, V. and G.E. Hinton. Rectified linear units improve restricted boltzmann machines. in Icml. 2010.
17	Simonyan, K. and A.J.a.p.a. Zisserman, Very deep convolutional networks for large-scale image recognition. 2014.
18	He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
19	Szegedy, C., et al. Rethinking the inception architecture for computer vision. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
20	Martin, D., et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. in Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001. 2001. IEEE.
21	Kim, J., J. Kwon Lee, and K. Mu Lee. Deeply-recursive convolutional network for image super-resolution. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
22	Hui, Z., X. Wang, and X. Gao. Fast and accurate single image super-resolution via information distillation network. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.