Abstract
Scene classification is often solved as a machine learning problem, where a classifier is first learned from training data, and class labels are then assigned to unlabelled testing data based on the outputs of the classifier. Generally, image descriptors are represented in high-dimensional space, where classifiers such as support vector machine (SVM) show good performance. However, SVM classifiers demand high computational power during model training. Extreme learning machine (ELM), whose synaptic weight matrix from the input layer to the hidden layer are randomly generated, has demonstrated superior computational efficiency. But the weights thus generated may not yield enough discriminative power for hidden layer nodes. Our recent study shows that the random mapping from the input layer to the hidden layer in ELM can be replaced by semi-random projection (SRP) to achieve a good balance between computational complexity and discriminative power of the hidden nodes. The application of SRP to ELM yields the so-called partially connected ELM (PC-ELM) algorithm. In this study, we apply PC-ELM to multi-class scene classification. Experimental results show that PC-ELM outperforms ELM in high-dimensional feature space at the cost of slightly higher computational complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Csurka, Gabriella, et al. “Visual categorization with bags of keypoints.” Workshop on statistical learning in computer vision, ECCV. Vol. 1. No. 1–22 (2004)
Lowe, David G. “Object recognition from local scale-invariant features.” Computer vision, 1999. The proceedings of the seventh IEEE international conference on. Vol. 2, (1999)
Oliva, Aude, Torralba, Antonio: Modeling the shape of the scene: A holistic representation of the spatial envelope. International journal of computer vision 42(3), 145–175 (2001)
Trunk, G.V.: A problem of dimensionality: A simple example. Pattern Analysis and Machine Intelligence, IEEE Transactions on 3, 306–307 (1979)
Boser, Bernhard E., Isabelle M. Guyon, and Vladimir N. Vapnik. “A training algorithm for optimal margin classifiers.” Proceedings of the fifth annual workshop on Computational learning theory (1992)
Joachims, Thorsten: Text categorization with support vector machines: Learning with many relevant features. Springer, Berlin Heidelberg (1998)
Huang, Guang-Bin, Qin-Yu Zhu, and Chee-Kheong Siew. “Extreme learning machine: a new learning scheme of feedforward neural networks.” Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on. Vol. 2 (2004)
Zhao, Rui, Mao, Kezhi: Semi-Random Projection for Dimensionality Reduction and Extreme Learning Machine in High-Dimensional Space. Computational Intelligence Magazine, IEEE 10(3), 30–41 (2015)
Bingham E. and Mannila H., Random projection in dimensionality reduction: Applications to image and text data, in Proc. 7th ACM SIGKDD Int. Conf. Knowledge Discovery Data Mining, pp. 245250 (2001)
Li, P, Hastie, T. J., and Church, K. W. Very sparse random projections, in Proc. 12th ACM SIGKDD Int. Conf. Knowledge Discovery Data Mining, pp. 287296 (2006)
Huang, Guang-Bin, et al. “Extreme learning machine for regression and multiclass classification.” Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on 42.2 pp. 513–529 (2012)
Cambria, E., Huang, G. B., Kasun, L. L. C., Zhou, H., Vong, C. M., Lin, J., ..., Liu, J. Extreme learning machines [trends & controversies]. Intelligent Systems, IEEE (2013)
Li, J-L. and Li, F-F. What, where and who? Classifying event by scene and object recognition. IEEE Intern. Conf. in Computer Vision (2007)
Chang, C-C., and Lin, C-J. LIBSVM : a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm (2011)
Bosch, A., Zisserman, A., Munoz, X.: Image classifcation using random forests and ferns. In Proc, ICCV (2007)
Vedaldi, A., Fulkerson, B. VLFeat: An open and portable library of computer vision algorithms, http://www.vlfeat.org/ (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, D., Zhao, R., Mao, K. (2016). Partially Connected ELM for Fast and Effective Scene Classification. In: Cao, J., Mao, K., Wu, J., Lendasse, A. (eds) Proceedings of ELM-2015 Volume 2. Proceedings in Adaptation, Learning and Optimization, vol 7. Springer, Cham. https://doi.org/10.1007/978-3-319-28373-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-28373-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28372-2
Online ISBN: 978-3-319-28373-9
eBook Packages: EngineeringEngineering (R0)