Abstract
Image classification is one of the most important problems for computer vision and machine learning. Many image classification methods have been proposed and applied to many application areas. But how to improve the performance of image classification is still an important research issue to be resolved. Feature extraction is the most important task of image classification, which affects the classification performance directly. Classical features extraction methods are designed manually according to color, shape or texture etc. They can only display the image characters partially and can’t be extracted objectively. Convolutional Neural Network (CNN), which is one kind of artificial neural networks, has already become current research focuses for image classification. Deep learning based on CNN can extract image features automatically. For improving image classification performance, a novel image classification method that combines CNN and parallel SVM is proposed. In the method, deep neural network based on CNN is used to extract image features. Extracted features are input to a parallel SVM based on MapReduce for image classification. It can improve the classification accuracy and efficiency markedly. The efficiency of the proposed method is illustrated through examples analysis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gurevich, B., Koryabkina, I.: Comparative analysis and classification of feature for image models. Pattern Recognit. Image Anal. 16(3), 265–297 (2006)
Pedrajas, N., Boyer, D.: Improving multiclass pattern recognition by the combination of two strategies. IEEE Trans. Pattern Recognit. Mach. Intell. 28(6), 1001–1006 (2006)
Hou, J., Gao, H., **a, Q., Qi, N.: Feature combination and the kNN framework in object classification. IEEE Trans. Neural Netw. Learn. Syst. 27(6), 1368–1378 (2016)
Sohn, M., Lee, S., Kim, H., Park, H.: Enhanced hand part classification from a single depth image using random decision forests. IET Comput. Vis. 10(8), 861–867 (2016)
Wu, Y., Yang, X., Plaza, A., Qiao, F., Gao, L.: Approximate computing of remotely sensed data: SVM hyperspectral image classification as a case study. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 9(12), 5806–5818 (2016)
Singh, K., Chaudhury, S.: Efficient technique for rice grain classification using back-propagation neural network and wavelet decomposition. IET Comput. Vis. 10(8), 780–787 (2016)
Dhale, V., Mahajan, A., Thakur, U.: A survey of feature extraction methods for image retrieval. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 10(2), 1–8 (2012)
Ayushi: A survey on feature extraction techniques. Int. J. Comput. Appl. 66(11), 43–46 (2013)
Kottawar, V., Rajurkar, A.: Moment preserving technique for color feature extraction in content based image retrieval. In: International Conference on Computer and Communications Technologies, pp. 1–5 (2014)
Yuan, W., Hamit, M., Kutluk, A., Yan, C., Li, L., Chen, J.: Feature extraction and analysis on **njiang uygur medicine image by using color histogram. In: IEEE International Conference on Medical Imaging Physics and Engineering, pp. 259–264 (2013)
Liang, J., Wang, M., Chai, Z., Wu, Q.: Different lighting processing and feature extraction methods for efficient face recognition. IET Image Proc. 8(9), 528–538 (2014)
**, T., Lou, J., Zhou, Z.: Extraction of landmine features using a forward-looking ground-penetrating radar With MIMO array. IEEE Trans. Geosci. Remote Sens. 50(10), 4135–4144 (2012)
Kuncheva, L., Faithfull, W.: PCA feature extraction for change detection in multidimensional unlabeled data. IEEE Trans. Neural Netw. Learn. Syst. 25(1), 69–80 (2014)
Kang, X., Li, S., Benediktsson, J.: Feature extraction of hyperspectral images with image fusion and recursive filtering. IEEE Trans. Geosci. Remote Sens. 52(6), 3742–3752 (2014)
Cireşan, D., Meler, U., Cambardella, L., Schmidhuber, J.: Deep, big, simple neural nets for handwritten digit recognition. Neural Comput. 22(12), 3207–3220 (2010)
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25(2), 1106–1114 (2012)
Sarikaya, R., Hinton, G., Deoras, A.: Application of deep belief networks for natural language understanding. IEEE/ACM Trans. Audio, Speech Lang. Process. 22(4), 778–784 (2014)
Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P.: Going deeper with convolutions. CoRR (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR (2015)
Bu, S., Liu, Z., Han, J., Wu, J., Ji, R.: Learning high-level feature by deep belief networks for 3-D model retrieval and recognition. IEEE Trans. Multimedia 16(8), 2154–2167 (2014)
Zheng, W., Zhu, J., Peng, Y., Lu, B.: EEG-based emotion classification using deep belief networks. In: IEEE International Conference on Multimedia and Expo, pp. 1–6 (2014)
Niu, X., Suen, C.: A novel hybrid CNN-SVM classifier for recognizing handwritten digits. Pattern Recogn. 45(4), 1318–1325 (2012)
Acknowledgements
This work is supported by the national science foundation (No. 61472230), National Natural Science Foundation of China (Grant No. 61402271), Shandong science and technology development plan (Grant No. 2016GGC01061, 2016GGX101029, J15LN54), Director Funding of Shandong Provincial Key Laboratory of computer networks.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Sun, Z., Li, F., Huang, H. (2017). Large Scale Image Classification Based on CNN and Parallel SVM. In: Liu, D., **e, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10634. Springer, Cham. https://doi.org/10.1007/978-3-319-70087-8_57
Download citation
DOI: https://doi.org/10.1007/978-3-319-70087-8_57
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70086-1
Online ISBN: 978-3-319-70087-8
eBook Packages: Computer ScienceComputer Science (R0)