Natural Image Classification Based on Improved Support Vector Machine

Abstract:

Local image representation based natural image classification is an important task. SIFT descriptors and bag-of-visterm (BOV)method have achieved very good results. Many studies focused on improving the representation of the image, and then use the support vector machine to classify and identify the image category. However, due to support vector machine its own characteristics, it shows inflexible and slower convergence rate for large samples，with the selection of parameters influencing the results for the algorithm very much. Therefore, this paper will use the improved support vector machine algorithm be based on ant colony algorithm in classification step. The method adopt dense SIFT descriptors to describe image features and then use two levels BOV method to obtain the image representation. In recognition step, we use the support vector machine as a classifier but ant colony optimization method is used to selects kernel function parameter and soft margin constant C penalty parameter. Experiment results show that this solution determined the parameter automatically without trial and error and improved performance on natural image classification tasks.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 2387-2391
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.2387
• Online since: June 2011
• Authors: Ying Jian Qi, Zhi Wei Ou, Bin Zhang, Ting Zhan Liu, Ying Li
• Keywords: Ant Colony Algorithm (ACA), Bag-of-Visterm, Natural Image Classification, Scale Invariance Feature Transform, Support Vector Machine (SVM)

References

[1] Anna Bosch, Andrew Zisserman. Scene Classification Using a Hybrid Generative/Discriminative Approach. In IEEE Trans. PAMI, vol. 30, No. 4, (2008).

[2] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In Proc. CVPR, vol. 2, (2006), p.2169–2178.

DOI: 10.1109/cvpr.2006.68

[3] L. Cao, L. FeiFei, Spatially coherent latent topic model for concurrent object segmentation and classification. ICCV, (2007) , pp.1-8.

[4] C. Dance, G. Csurka, C. Bray L. Fan. Visual categorization with bags of keypoints. In Proc. ECCV, ( 2004), p.1–22.

[5] J. Sivic, A. Zisserman, Video google: A text retrieval approach to object matching in videos, in ICCV , 03, Vol(2), (2003), pp.1470-1477.

DOI: 10.1109/iccv.2003.1238663

[6] D. G. Lowe, Distinctive image features from scale-invariant keypoints, Int. J. Computer. Vision, 60(2), (2004), pp.91-110.

DOI: 10.1023/b:visi.0000029664.99615.94

[7] F. Jurie, B. Triggs, Creating efficient codebooks for visual recognition, ICCV'2005. (2005), pp.604-610.

DOI: 10.1109/iccv.2005.66

[8] E. Nowak, F. Jurie, B. Triggs, Sampling strategies for bag-of-features image classification, " in ECCV06, (2006), pp.490-503.

[9] Angiulli, F. Astorino, A. Scaling Up Support Vector Machines Using Nearest Neighbor Condensation, IEEE Transactions on Neural Networks, 21(2), (2010), pp.351-357.

DOI: 10.1109/tnn.2009.2039227

[10] Grinblat, G. L.; Uzal, L. C.; Ceccatto, H. A.; Granitto, P. M., Solving Nonstationary Classification Problems With Coupled Support Vector Machines IEEE Transactions on Neural Networks, 22(1), (2011), pp.37-51.

DOI: 10.1109/tnn.2010.2083684

[11] S. Lazebnik, C. Schmid, and J. Ponce, Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories, in Computer Vision and Pattern Recognition, (2006), pp.2169-2178.

DOI: 10.1109/cvpr.2006.68

[12] D. Larlus, F. Jurie, Latent mixture vocabularies for object categorization and segmentation, Image and Vision Computing, In Press, Corrected Proof, (2009), pp.759-768.

DOI: 10.1016/j.imavis.2008.04.022

[13] Y. Liu, J. Rong, R. Sukthankar, and F. Jurie, Unifying discriminative visual codebook generation with classifier training for object category recognition, in Computer Vision and Pattern Recognition, (2008), pp.1-8.

DOI: 10.1109/cvpr.2008.4587504

[14] C. J. C. Burges. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2), (1998), p.121–167.

[15] Dorigo M, Maniezzo V, Colorni A. Ant System: Op timization by a Colony of Coorperating Agents, IEEE Transactions on Systems, Man, and Cybernetics2 Part B, 26(1), (1996), pp.29-41.

DOI: 10.1109/3477.484436

[16] Pedro Quelhas, Jean-Marc Odobez, Multi-level local descriptor quantization for Bag-of-Visterms image representation, in CIVR07, (2007), pp.242-249.

DOI: 10.1145/1282280.1282319

[17] L. Fei-Fei and P. Perona. A Bayesian hierarchical model for learning natural scene categories. In In Proceedings of IEEE Conference in Computer Vision and Pattern Recognition (CVPR), (2005), p.524–531.

DOI: 10.1109/cvpr.2005.16