Abstract
Spatial pyramid matching (SPM) model is an extension of the bag-of-visual words (BoW) model for local feature encoding. It firstly partitions the image into increasingly fine sub-regions, and then concatenates the histograms within each sub-region. However, the SPM model does not consider the spatial information differences between sub-regions explicitly. To make use of this information, we exploit a novel descriptor called spatial difference. In the process of promoting the performance of image classification, this descriptor is mainly used to concatenate the histograms of bag-of-visual words model under spatial pyramid matching framework. Finally, we conduct image classification experiments on several public datasets to demonstrate the effectiveness of the proposed scheme.
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
Sivic, J., Zisserman, A.: Video google: a text retrieval approach to object matching in videos. In: Proceedings of ICCV, pp. 1470–1477. IEEE (2003)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognition natural scene categories. In: Proceedings of CVPR, pp. 2169–2178 (2006)
Teng, K., Wang, J., Tian, Q., Lu, H.: Improving scene classification with weakly spatial information. In: Proceedings of ICIP, pp. 3259–3263 (2013)
Grauman, K., Darrell, T.: Pyramid match kernels: discriminative classification with sets of image features. In: Proceedings of ICCV, pp. 725–760 (2005)
Smeulders, A., Gemert, J., Veenman, C., Geusebroek, J.: Visual word ambiguity. IEEE Trans. Pattern Anal. Mach. Intell. 32(7), 1271–1283 (2010)
Yang, J., Yu, K., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of CVPR (2009)
Gao, S., Tsang, I., Chia, L.: Local features are not lonely-Laplacian sparse coding for image classification. In: Proceedings of CVPR (2010)
Wang, J., Yang, J., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In Proceedings of CVPR (2010)
Chen, Q., Song, Z., Hua, Y., Huang, Z., Yan, S.: Hierarchical matching with side information for image classification. In: Proceedings of CVPR, pp. 3426–3433 (2012)
Yao, B., Khosla, A., Fei-Fei, L.: Combining randomization and discriminative for fine-grained image categorization. In: Proceedings of CVPR, pp. 1577–1584 (2012)
Zhang, N., Farrell R., Darrell, T.: Pose pooling kernels for sub-category recognition. In: Proceedings of CVPR, pp. 3665–3672 (2012)
Zhang, C., Liu, J., Tian, Q., Han, Y., Lu, H., Ma, S.: A boosting, sparsity-constrained bilinear model for object recognition. IEEE Multimedia 2, 58–68 (2012)
Bao, C., He, L.: Linear spatial pyramid matching using non-convex and non-negative sparse coding for image classification (2015). arXiv:1504.06897v1 [cs. CV]
Pasolli, E., Melgoni, F., Tuia, D., Pacifici, F., Emery, W.J.: SVM active learning approach for image classification using spatial information. IEEE Trans. Geosci. Remote Sens. 52(4), 2217–2233 (2014)
Jia, S., Xie, Y., Zhu, Z.: Integration of spatial and spectral information by means of sparse representation-based classification for hyper spectral imagery. In: Proceedings of the 18th Asia Pacific Symposium of Intelligent and Evolutionary Systems, Proceedings in Adaption, Learning and Optimization (2015). doi:10.1007/978-3-319-13356-0_10
Zhu, C., Yang, S., Zhao, Q., Cui, S., Wen, N.: Robust semi-supervised kernel-FCM algorithm incorporating local information for remote sensing image classification. J. Indian Soc. Remote Sens. 42, 35–49 (2014)
Zhang, C., Chen, J., Liu, J.: Object categorization in sub-semantic space. Neurocomputing 142, 248–255 (2014)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset, Caltech-256 Technical report UCB/CSD-04-1366 (2007)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (61202325, 61303154, 61379100, 61370169, 60873104).
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
Li, Y., Xu, J., Zhang, Y., Zhang, C., Yin, H., Lu, H. (2016). Image Classification Using Spatial Difference Descriptor Under Spatial Pyramid Matching Framework. In: Tian, Q., Sebe, N., Qi, GJ., Huet, B., Hong, R., Liu, X. (eds) MultiMedia Modeling. MMM 2016. Lecture Notes in Computer Science(), vol 9516. Springer, Cham. https://doi.org/10.1007/978-3-319-27671-7_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-27671-7_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27670-0
Online ISBN: 978-3-319-27671-7
eBook Packages: Computer ScienceComputer Science (R0)