Abstract
Compressed sensing theory is widely used in image and video signal processing because of its low coding complexity, resource saving, and strong anti-interference ability. Although the compression sensing theory solves the problems brought by the traditional signal processing methods to a certain extent, it also encounters some new problems: the reconstruction time is long and the algorithm complexity is high. In order to solve these problems and further improve the quality of image processing, a new convolutional neural network structure CombNet is proposed, which uses the measured value of compression sensing as the input of the convolutional neural network, and connects a complete connection layer to get the final Output. Experiments show that CombNet has lower complexity and better recovery performance. At the same sampling rate, the peak signal-to-noise ratio (PSNR) is 12.79% – 52.67% higher than Tval3 PSNR, 16.31%–158.37% higher than D-AMP, 1.00%–3.79% higher than DR2-Net, and 0.06%–2.60% higher than FCMN. It still has good visual appeal when the sampling rate is very low (0.01).
Article PDF
Similar content being viewed by others
References
R.G. Baraniuk, E.J. Candes, R. Nowak, et al., Compressive Sampling, IEEE Signal Processing Magazine, 25 (2008), 1433–1452
M. Fornasier, H. Rauhut, Compressive sensing, in: O. Scherzer (Eds.), Handbook of Mathematical Methods in Imaging, Springer, New York, 2011, pp. 187–228.
J. Romberg, Imaging via compressive sampling, Signal Process. Mag. IEEE. 25 (2008), 14–20
S. Ji, D. Dunson, L. Carin, Multitask compressive sensing. IEEE Trans. Signal Process. 57 (2009), 92–106
A. Mousavi, A.B. Patel, R.G. Baraniuk, A deep learning approach to structured signal recovery, in 2015 53rd Annual Allerton Conference on Communication, Control, and Computing, IEEE, Monticello, IL, USA, 2015, pp. 1336–1343.
A. Mousavi, R.G. Baraniuk, Learning to invert: signal recovery via deep convolutional networks, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, LA, 2017.
K. Kulkarni, S. Lohit, P. Turaga, et al., ReconNet: non-iterative reconstruction of images from compressively sensed measurements, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Las Vegas, NV, 2016.
X.M. Xie, C. Wang, J. Du, et al., Full image recover for block-based compressive sensing, in 2018 IEEE International Conference on Multimedia and Expo (ICME), San Diego, CA, 2018, pp. 1–6.
A.M. Taqi, F. Al-Aoo, M. Mariofanna, et al., Classification and discrimination of focal and non-focal EEG signals based on deep neural network, in 2017 International Conference on Current Research in Computer Science & Information Technology, IEEE, Slemani, Iraq, 2017.
Y.Q. Jia, E. Shelhamer, J. Donahue, et al., Caffe: convolutionalal architecture for fast feature embedding, in Proceedings of the 22nd ACM International Conference on Multimedia, ACM, Orlando, Florida, USA, 2014, pp. 675–678.
C.B. Li, W.T. Yin, H. Jiang, et al., An efficient augmented lagrangian method with applications to total variation minimization, Comput. Optim. Appl. 56 (2013), 507–530
C.A. Metzler, A. Maleki, R.G. Baraniuk, From denoising to compressed sensing, IEEE Trans. Inf. Theory. 62 (2016), 5117–5144
H.T. Yao, F. Dai, D. Zhang, et al., DR2-Net: deep residual reconstruction network for image compressive sensing, arXiv preprint, arXiv:1702.05743, 2017.
J. Du, X.M. Xie, C. Wang, et al., Fully-convolutional measurement network for compressive sensing image reconstruction, arXiv preprint arXiv:1712.01641, 2017.
X.M. Xie, Y. Wang, G. Shi, et al., Adaptive measurement network for CS image reconstruction, in CCF Chinese Conference on Computer Vision, Tianjin, China, 2017, pp. 407–417.
Y. Jia, The analysis of compressive sensing theory, in 2014 9th International Conference on P2p, IEEE Computer Society, Guangdong, China, 2014.
D.L. Donoho, Compressed sensing, IEEE Trans. Inf. Theory. 52 (2006), 1289–1306
E.J. Candes, B.W. Michael, An introduction to compressive sampling, IEEE Signal Process. Mag. 25 (2008), 21–30
E.J. Candes, J. Romberg, T. Tao, Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information, IEEE Trans. Inf. Theory. 52 (2006), 489–509
A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, In Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.
K. He, X. Zhang, S. Ren, et al., Delving deep into rectifiers: surpassing human-level performance on imageNet classification, in 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015, pp. 1026–1034.
C. Dong, C.C. Loy, K. He, X. Tang, Learninga deep convolutional network for image superresolution, In Euro. Conf. Comp. Vision, 2014, 184–199.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
About this article
Cite this article
Liu, Y., Liu, S., Li, C. et al. Compressed Sensing Image Reconstruction Based on Convolutional Neural Network. Int J Comput Intell Syst 12, 873–880 (2019). https://doi.org/10.2991/ijcis.d.190808.001
Received:
Accepted:
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.2991/ijcis.d.190808.001