Abstract
Scene classification aims at grouping images into semantic categories. In this article, a new scene classification method is proposed. It consists of regularized auto-encoder-based feature learning step and SVM-based classification step. In the first step, the regularized auto-encoder, imposed with the maximum scatter difference (MSD) criterion and sparse constraint, is trained to extract features of the source images. In the second step, a multi-class SVM classifier is employed to classify those features. To evaluate the proposed approach, experiments based on 8-category sport events (LF data set) are conducted. Results prove that the introduced approach significantly improves the performance of the current popular scene classification methods.
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
References
Serrano-Talamantes JF, Aviles-Cruz C, Villegas-Cortez J, Sossa-Azuela JH (2013) Self-organizing natural scene image retrieval. Expert Syst Appl 40(7):2398–2409
Qin J, Yung NHC (2010) Scene categorization via contextual visual words. Pattern Recogn 43:1874–1888
Song F, Zhang D, Chen Q, W Jizhong (2007) Face recognition based a novel linear discriminant criterion. Pattern Anal Applic 10:165–174
Deng J, Zhang Z, Marchi E, Schuller B (2013) Sparse auto-encoder-based feature transfer learning for speech emotion recognition. In: Affective computing and intelligent interaction, human association conference, pp 511–516
Krizhevsky A, Hinton GE (2010) Factored 3-way restricted Boltzmann achiness for modelling natural images. In: International conference on artificial intelligence and statistics, pp 621–628
Chen Y, Xu W, Wu J, Zhang G (2012) Fuzzy maximum scatter discriminant analysis in image segmentation. J Convergence Inf Technol 7(5)
Yang J, Yang JY (2003) Why can LDA be performed in PCA transformed space. Pattern Recognit 2:563–566
Li LJ, Su H, Fei-Fei L (2007) What, where and who? Classification events by scene and object recognition. In: Eleventh IEEE international conference on computer vision, pp 1–8
Wu J, Rehg JM (2009) Beyond the Euclidean distance: creating effective visual codebooks using the histogram intersection kernel. In: Twelfth IEEE international conference on computer vision, pp 630–637
Li LJ, Su H, Lim YW, Fei-Fei L (2010) Objects as attributes for scene classification. In: European conference computer vision, pp 1–13
Nakayama H, Harada T, Kuniyoshi Y (2010) Global Gaussian approach for scene categorization using information geometry. In: IEEE conference on computer vision and pattern recognition, pp 2336–2343
Li LJ, Su H, Xing EP, Fei-Fei L (2010) Object bank: a high-level image representation for scene classification & semantic feature sparsification. In: Proceedings of the neural information processing systems
Zhou L, Zhou Z, Hu D (2013) Scene classification using a multi-resolution bag-of-features model. Pattern Recogn 46:424–433
Gao SH, Tsang IWH, Chia LT (2010) Kernel sparse representation for image classification and face recognition. In: European conference computer vision, pp 1–14
Huang GB, Lee H, Learned-Miller E (2012) Learning hierarchical representations for face verification with convolutional deep belief networks. In: IEEE Conference on computer vision and pattern recognition, pp 2518–2525
Lin SW, Ying KC, Chen SC, Lee ZJ (2008) Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst Appl 35(4):1817–1824
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, Y., Li, N., Yin, H., Chai, Y., Jiao, X. (2016). Scene Classification Based on Regularized Auto-Encoder and SVM. In: Jia, Y., Du, J., Li, H., Zhang, W. (eds) Proceedings of the 2015 Chinese Intelligent Systems Conference. Lecture Notes in Electrical Engineering. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48365-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-662-48365-7_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48363-3
Online ISBN: 978-3-662-48365-7
eBook Packages: EngineeringEngineering (R0)