Image Classification Based on Sparse Autoencoder and Support Vector Machine

doi:10.16182/j.issn1004731x.joss.201808023

Abstract

Abstract: A new algorithm of image classification based on the sparse autoencoder and the support vector machine was proposed in view of the drawbacks that the single layer sparse autoencoder for feature learning is easy to lose the deep abstract feature and the features lack the robustness. The deep sparse autoencoder is constructed to learn each image layer and the feature of each layer is automatically extracted. The each feature weights and the reorganized set of feature are obtained according to the feature weighting method. By combining the strong global search ability of genetic algorithm and the excellent performance of support vector machine, the image classification is completed efficiently and accurately. The experimental results show that the proposed algorithm can automatically learn the deep feature of the image, and the reorganized feature has high feature discrimination ability, which effectively improves the accuracy of image classification.

Key words: sparse autoencoder, feature learning, genetic algorithm, support vector machine, image classification

CLC Number:

TP391.41

Liu Fang, Lu Lixia, Wang Hongjuan, Wang Xin. Image Classification Based on Sparse Autoencoder and Support Vector Machine[J]. Journal of System Simulation, 2018, 30(8): 3007-3014.

References

[1] Xiong M, Chen J, Wang Z, et al.Deep Feature Representation via Multiple Stack AutoEnco-ders[M]. Advances in Multimedia Information Processing-PCM, 2015: 275-284.
[2] Chen Kunjin, Hu Jun, He Jinliang, et al.A Framework for Automatically Extracting Overvoltage Features Based on Sparse Autoencoder[J]. IEEE Transactions on Smart Grid (S1949-3053), 2016: 1-1.
[3] Tao Chao, Pan Hongbo, Li Yansheng, et al.Unsupervised Spectral-Spatial Feature Learning With Stacked Sparse Autoencoder for Hyprspectral Imagery Classification[J]. IEEE Geoscience and Remote Sensing Letters (S1545-598X). 2015: 2438-2442.
[4] Yin Hongpeng, Jiao Xuguo, Chai Yi, et al.Scene classification based on single-layer SAE and SVM[J]. Expert Systems with Applications (S0957-4174), 2015, 42(7): 3368-3380.
[5] Esam Othman, Yakoub Bazi, Naif Alajlan, et al.Using convolutional features and a sparse autoencoder for land-use scene classification[J]. International Journal of Remote Sensing (S0143-1161), 2016: 2149-2167.
[6] Makhzani A, Frey B.Winner-Take-All Autoencoders[J]. Eprint Arxiv(S1049-5258), 2014: 2773-2781.
[7] H Lee, R Grosse, R Ranganath, et al.Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations-[C]// Proceedings of the 26th Annual International Conference on Machine Learning. Canada, 2009: 609-616.
[8] Pascal Vincent, Hugo Larochelle, Yoshua Bengio, et al.Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research (S1532-4435), 2010: 3371-3408.
[9] Du Bo, Xiong Wei, Wu Jia, et al.Stacked Convolutional Denoising AutoEncoders for Feature Representation[J]. IEEE Transactions on Cybernetics(S2168-2267), 2016: 1-11.
[10] Pascal Vincent, Hugo Larochelle, Yoshua Bengio, et al.Extracting and composing robust features with denoising autoencoders[C]// Proceedin-ings of the 25th International Conference on Machine Learning, 2008: 1096-1103.
[11] Chow R, Zhong W, Blackmon M, et al.An efficient SVM-GA feature selection model for large healthcare databases[C]// Genetic and Evolutionary Computation Conference. USA, 2008: 1373-1380.
[12] Rifai S, Vincent P, Muller X, et al.Contractive Auto-Encoders: Explicit Invariance During Feature Extraction[C]// Proceedings of the 28th International Conference on Machine Learning. 2011: 833-840.
[13] Ju Y, Guo J, Liu S.A Deep Learning Method Combined Sparse Autoencoder with SVM[C]// International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery. IEEE, 2015: 257-260.
[14] Bengio Y, Lamblin P, Popovici D, et al.Greedy layer-wise training of deep networks[C]// Proceedings of the 19th International Conference on Neural Information Processing Systems. Canada, 2007: 153-160.
[15] Dai C.SVM Visual Classification Based on Weighted Feature of Genetic Algorithm[C]// Sixth International Conference on Intelligent Systems Design and Engineering Applications. IEEE Computer Society, 2015: 786-789.
[16] Huang C L, Wang C G.A GA-based feature selection and parameters optimization for support vector machines[J]. Expert Systems with Applications (S0957-4174), 2006: 231-240.