Abstract
For a large amount of image data, an image classification method based on improved deep belief network (IDBN) and improved extreme learning machine (YELM) was proposed. Firstly, IDBN was used to simplify the complex high-dimensional data to lower dimensions space, and get the main inherent feature of the images with lower dimension. Then YELM was used to classify data after the dimension reduction. The proposed IDBN-YELM method has a significant improvement in classification accuracy. Extensive experiments were performed using challenging dataset and results were compared against the models such as DBN, YELM, IDBN-ELM. Though a lot of comparative experiments on the street view house numbers (SVHN) dataset, the results show that the IDBN-YELM has the high classification accuracy for the problem of large-scale image classification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kamusoko, C.: Image classification. In: Kamusoko, C. (ed.) Remote Sensing Image Classification in R. SG, pp. 81–153. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-8012-9_4
Li, C., Wang, K., Xu, N.: A survey for the applications of content-based microscopic image analysis in microorganism classification domains. Artif. Intell. Rev. 51(4), 577–646 (2017). https://doi.org/10.1007/s10462-017-9572-4
Liu, X., Zhang, R., Meng, Z., Hong, R., Liu, G.: Correction to: on fusing the latent deep CNN feature for image classification. World Wide Web 22, 1887 (2019)
Zheng, S., Zhang, Y., Liu, W., Zou, Y.: Improved image representation and sparse representation for image classification. Appl. Intell. 50(6), 1687–1698 (2020). https://doi.org/10.1007/s10489-019-01612-3
Lecun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541–551 (1989)
Kussul, E.M., Baidyk, T.N., Wunsch II, D.C., Makeyev, O., Martn, A.: Permutation coding technique for image recognition systems. IEEE Trans. Neural Netw. 17, 1566–1579 (2006)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504 (2006)
Desai, S., Sinha, D., El-Sharkawy, M.: Image classification on NXP i.MX RT1060 using ultra-thin MobileNet DNN (2020)
Geng, Z., Li, Z., Han, Y.: A new deep belief network based on RBM with glial chains. Inf. Sci. 463–464, 294–306 (2018)
Prasetio, M.D., Hayashida, T., Nishizaki, I., Sekizaki, S.: Deep belief network optimization in speech recognition. In: 2017 International Conference on Sustainable Information Engineering and Technology (SIET), pp. 138–143 (2017)
Wei, P., Li, Y., Zhang, Z., Hu, T., Li, Z., Liu, D.: An optimization method for intrusion detection classification model based on deep belief network. IEEE Access 7, 87593–87605 (2019)
Zhang, Y., Li, P., Wang, X.: Intrusion detection for IoT based on improved genetic algorithm and deep belief network. IEEE Access 7, 31711–31722 (2019)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: a new learning scheme of feedforward neural networks. In: 2004 IEEE International Joint Conference on Neural Networks (2004)
Kannojia, S.P., Jaiswal, G.: Ensemble of hybrid CNN-ELM model for image classification. In: 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN), pp. 538–541 (2018)
Huang, G.B., Zhu, Q.Y., Siew, C.K.J.N.: Extreme learning machine: theory and applications. Neurocomputing 70, 489–501 (2006)
Huang, G.B.J.C.C.: An insight into extreme learning machines random neurons, random features and kernels. Cogn. Comput. 6, 1–15 (2014). https://doi.org/10.1007/s12559-014-9255-2
Zhang, H., Yin, Y., Zhang, S., Sun, C.: An improved ELM algorithm based on PCA technique. In: Cao, J., Mao, K., Cambria, E., Man, Z., Toh, K.-A. (eds.) Proceedings of ELM-2014 Volume 2. PALO, vol. 4, pp. 95–104. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-14066-7_10
Peng, Y., Lu, B.L.J.N.: Discriminative extreme learning machine with supervised sparsity preserving for image classification. Neurocomputing 261, 242–252 (2017)
Lendasse, A., Man, V.C., Miche, Y., Huang, G.B.: Advances in extreme learning machines (ELM2014). Neurocomputing 174, 1–3 (2016)
Yuan, Y., Wang, Y., Cao, F.J.N.: Optimization approximation solution for regression problem based on extreme learning machine. Neurocomputing 74, 2475–2482 (2011)
Barra, A., Genovese, G., Sollich, P., Tantari, D.J.P.R.E.: Phase diagram of restricted Boltzmann machines and generalized Hopfield networks with arbitrary priors. Phys. Rev. 97, 022310 (2018)
Leng, B., Zhang, X., Yao, M., Xiong, Z.: 3D object classification using deep belief networks. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014. LNCS, vol. 8326, pp. 128–139. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-04117-9_12
Luo, X., Xu, S.: Forest mapping from hyperspectral image using deep belief network. In: 2019 15th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN), pp. 395–398 (2019)
Ma, Y., Bao, C., Xia, BJJoTU: Speaker segmentation based on discriminative deep belief networks. J. Tsinghua Univ. (Sci. Technol.) 53, 804–807 (2013)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.: Reading digits in natural images with unsupervised feature learning. In: NIPS (2011)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, C., Li, Z., Nie, R., Wang, L., Zhao, H. (2020). Image Classification Based on Deep Belief Network and YELM. In: Huang, DS., Bevilacqua, V., Hussain, A. (eds) Intelligent Computing Theories and Application. ICIC 2020. Lecture Notes in Computer Science(), vol 12463. Springer, Cham. https://doi.org/10.1007/978-3-030-60799-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-60799-9_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60798-2
Online ISBN: 978-3-030-60799-9
eBook Packages: Computer ScienceComputer Science (R0)