Abstract
The work proposed in this paper is motivated by the need to develop powerful approaches for scene classification which is a challenging problem mainly due to varying conditions. In this paper, we are mostly interested in automatically assigning a scene image to a semantic category when RGB channels and near infrared information are simultaneously available. We represent images by a collection of local image patches that we use to learn a global generalized Gaussian mixture (GGM) using the split and merge expectation-maximization (SMEM) algorithm. Using this approach, we built an effective scene classification system capable of handling outliers and noise level in the data. Extensive experiments show the merits of the proposed framework.
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
Schaul, L., Fredembach, C., S\(\ddot{u}\)sstrunk, S.: Color image dehazing using the near-infrared. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), pp. 1629–1632 (2009)
Salamati, N., Larlus, D., Csurka, G.: Combining visible and near-infrared cues for image categorisation. In: Proceedings of the British Machine Vision Conference (BMVC) (2011)
Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145–175 (2001)
Vogel, J., Schiele, B.: Natural scene retrieval based on a semantic modeling step. In: Enser, P.G.B., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol. 3115, pp. 207–215. Springer, Heidelberg (2004)
Quelhas, P., Monay, F., Odobez, J.M., Gatica-Perex, D., Tuytelaars, T., Van Gool, L.: Modeling Scenes with local descriptors and latent aspects. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 883–890 (2005)
Allili, M.S., Bouguila, N., Ziou, D.: Finite general Gaussian mixture modeling and application to image and video foreground segmentation. J. Electron. Imaging 17(1), 1–13 (2008)
Ueda, N., Nakano, R., Ghahramani, Z., Hinton, G.E.: SMEM algorithm for mixture models. Neural Comput. 12(9), 2109–2128 (2000)
Haralick, R., Shanmugam, K., Dinstein, I.: Texture features for image classification. IEEE Trans. Syst., Man, Cybern., SMC 3(6), 610–621 (1973)
Lu, L., Toyama, K., Hager, G.D.: A two level approach for scene recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 688–695 (2005)
Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Mach. Learn. 42(1/2), 177–196 (2001)
Chang, C.-C., Li, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intel. Syst. Technol. 2(27), 1–27 (2011)
Brown, M., S\(\ddot{u}\)sstrunk, S.: Multispectral SIFT for scene category recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 177–184 (2011)
Acknowledgment
The completion of this research was made possible thanks to the Natural Sciences and Engineering Research Council of Canada (NSERC).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Elguebaly, T., Bouguila, N. (2015). Semantic Scene Classification with Generalized Gaussian Mixture Models. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2015. Lecture Notes in Computer Science(), vol 9164. Springer, Cham. https://doi.org/10.1007/978-3-319-20801-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-20801-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20800-8
Online ISBN: 978-3-319-20801-5
eBook Packages: Computer ScienceComputer Science (R0)