Image compression and encryption scheme based on deep learning
/ 0
- Details
- Category: Information technologies, systems analysis and administration
- Last Updated on 19 January 2017
- Published on 19 January 2017
- Hits: 4387
Authors:
Fei Hu, School of Computer and Information Science, Southwest University, Chongqing, China, Network Centre, Chongqing University of Education, Chongqing, China
Changjiu Pu, Network Centre, Chongqing University of Education, Chongqing, China
Haowei Gao, The Webb Schools, 1175 West Baseline Road Claremont, CA 91711, USA
Mengzi Tang, School of Computer and Information Science, Southwest University, Chongqing, China
Li Li, School of Computer and Information Science, Southwest University, Chongqing, China
Abstract:
Purpose. With the growing demands of image processing on the Internet, image compression and encryption have been playing an important role in image protection and transfering. In this paper we will investigate deep learning technology in image compression, and chaotic logistic map in image encryption, to obtain a scheme in image compression and encryption. We have evaluated this scheme with some performance measures and results show it is effective.
Methodology. We formulate the scheme using deep learning and chaos. With the deep learning technology, levels of features are extracted from an image and a certain level of features can be used as a compressed representation of the image. Chaos is used to encrypt the compressed image.
Findings. We first introduceda five-layer Stacked Auto-Encoder model, which is trained by the Back Propogration method, and then we obtained the compressed representation of an image. By using the logistic map method, a pseudo-stochastic sequence is generated to encrypt the compressed image.
Originality. We conducted a study of image compression and encryption. Image characteristics are extracted from an arbitrary level of our deep learning model, and they are used as the compressed representation of the image. The research on this aspect has not been found at present.
Practical value. We have evaluated this scheme on several randomly selected images. And results show it is robust and can be widely used for most images.
References/Список літератури
1. Zhang, Chunhong, 2016. Application of Multi-Wavelet Analysis in Image Compression. Revista Tecnica De La Facultad De Ingenieria Universidad Del Zulia, No. 39(3), pp. 760–82.
2. Fischer, A., and Igel, C., 2014. Training restricted Boltzmann machines: An introduction. Pattern Recognition, No. 47(1), рр. 25–39.
3. Ma, X., and Wang, X., 2016. Average Contrastive Divergence for Training Restricted Boltzmann Machines. Entropy, No. 18(1), pp. 35–49.
4. Sarangi, P.P., Sahu, A., and Panda, M., 2013. A hybrid differential evolution and back-propagation algorithm for feedforward neural network training. International Journal of Computer Applications, No. 84(14), pp. 1–9.
5. Liu, Q., and Yang, S., 2014. Stability and bifurcation of a class of discrete-time Cohen–Grossberg neural networks with discrete delays. Neural Processing Letters, No. 40(3), pp. 289–300.
6. Sarmah, H.K.R., Das, M.C., and Baishya, T.K.R., 2014. Neimark-Sacker bifurcation in delayed logistic map. International Journal of Applied Mathematics & Statistical Sciences, No. 3(1), pp.19–34.
7. LeCun, Y., Bengio, Y., and Hinton, G., 2015. Deep learning. Nature, No. 521(7553), pp. 436–444.
8. Tiwari, M., and Gupta, B., 2015. Image Denoising Using Spatial Gradient Based Bilateral Filter and Minimum Mean Square Error Filtering. Procedia Com puter Science, No. 54, pp. 638–645.
9. Karamchandani, S.H., Gandhi, K.J., Gosalia, S.R., Madan, V.K., Merchant, S.N., and Desai, U.B., 2015. PCA encrypted short acoustic data inculcated in Digital Color Images. International Journal of Computers Communications & Control, No. 10(5), pp. 678–685.
10. Zhang, Y.Q., and Wang, X.Y., 2015. A new image encryption algorithm based on non-adjacent coupled map lattices. Applied Soft Computing, No. 26, pp. 10–20.
 06_2016_Fei
|
|
 2017-01-19  1.54 MB  958 |
|
Archive