Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new algorithm model. The classical convolutional neural network is improved, the convolution kernel size is adjusted, and the parameters are reduced; the pooling layer is added to reduce the dimension. Reduced computational complexity, increased learning rate, and reduced training time. The iterative back-projection algorithm is combined with the convolutional neural network to create a new algorithm model. The experimental results show that compared with the traditional facial illusion method, the proposed method can obtain better performance.
References
[1]
Baker, S. and Kanade, T. (2000) Hallucinating Faces. IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, 28-30 March 2000, 83-88. https://doi.org/10.1109/AFGR.2000.840616
[2]
Freeman, W.T. and Pasztor, E.C. (1999) Learning Low-Level Vision. International Conference on Computer Vision, Kerkyra, 20-27 September 1999, 1182-1189. https://doi.org/10.1109/ICCV.1999.790414
[3]
Dong, C., et al. (2014) Learning a Deep Convolutional Network for Image Super-Resolution. European Conference on Computer Vision, 184-199.
[4]
Irani, M. and Peleg, S. (1990) Super Resolution from Image Sequences. 10th International Conference on Pattern Recognition, Atlantic City, 16-21 June 1990. https://doi.org/10.1109/ICPR.1990.119340
[5]
Plank, J., Beck, M. and Elwasif, W. (1999) IBP: The Internet Backplane Protocol, 93, 679-688.
[6]
Lei, J., et al. (2018) An Image Guided Algorithm for Range Map Super-Resolution. Society of Photo-Optical Instrumentation Engineers, 43. https://doi.org/10.1117/12.2288074
[7]
Dong, C., et al. (2016) Image Super-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, 295-307. https://doi.org/10.1109/TPAMI.2015.2439281
[8]
Zhou, S.K., Chellappa, R. and Moghaddam, B. (2004) Intra-Personal Kernel Space for Face Recognition. IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, 19 May 2004, 235-240. https://doi.org/10.1109/AFGR.2004.1301537
[9]
Yan, W.U. (2009) One Improved Super-Reconstruction Algorithm Based on IBP Theory. Infrared, 12, 11-15.
[10]
Gao, H., Zeng, J. and Zhao, Y. (2016) Super-Resolution Reconstruction Algorithm Based on Adaptive Convolution Kernel Size Selection. Applications of Digital Image Processing XXXIX, Article ID: 997120.
[11]
Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) ImageNet Classification with Deep Convolutional Neural Networks. International Conference on Neural Information Processing Systems, 1097-1105.
[12]
Wang, N., et al. (2014) A Comprehensive Survey to Face Hallucination. International Journal of Computer Vision, 106, 9-30. https://doi.org/10.1007/s11263-013-0645-9
[13]
Grm, K., et al. (2018) Face Hallucination Using Cascaded Super-Resolution and Identity Priors.
[14]
Jiang, J., et al. (2018) Deep CNN Denoiser and Multi-Layer Neighbor Component Embedding for Face Hallucination. IJCAI. https://doi.org/10.24963/ijcai.2018/107
[15]
Shi, J., et al. (2018) Hallucinating Face Image by Regularization Models in High-Resolution Feature Space. IEEE Transactions on Image Processing, 27, 2980-2995. https://doi.org/10.1109/TIP.2018.2813163
[16]
Ma, X., Zhang, J. and Qi, C. (2010) Hallucinating Face by Position-Patch. Pattern Recognition, 43, 2224-2236. https://doi.org/10.1016/j.patcog.2009.12.019
[17]
Ruangsang, W. and Aramvith, S. (2017) Efficient Super-Resolution Algorithm Using Overlapping Bicubic Interpolation. 6th Global Conference on Consumer Electronics, Nagoya, 24-27 October 2017, 1-2.
[18]
Cao, Q.I., et al. (2016) Super-Resolution Algorithm of Infrared Video Image Based on Sparse Representation.
[19]
Yang, J., et al. (2010) Image Super-Resolution via Sparse Representation. IEEE Transactions on Image Processing, 19, 2861-2873. https://doi.org/10.1109/TIP.2010.2050625
[20]
Wang, Y., et al. (2018) Improved Algorithm of Image Super Resolution Based on Residual Neural Network. Journal of Computer Applications.
[21]
Wang, Y., et al. (2016) End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks.
