Abstract
For the task of visual-based automatic product image classification for e-commerce, this paper constructs a set of support vector machine (SVM) classifiers with different model representations. Each base SVM classifier is trained with either different types of features or different spatial levels. The probability outputs of these SVM classifiers are concatenated into feature vectors for training another SVM classifier with a Gaussian radial basis function (RBF) kernel. This scheme achieves state-of-the-art average accuracy of 86.9% for product image classification on the public product dataset PI 100.
Similar content being viewed by others
References
Tomasik B, Thiha P, Turnbull D. Tagging products using image classification [C]//Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Boston, USA: ACM Press, 2009: 792–793.
Jia Shi-jie, Kongv Xiang-wei, Fu Hai-yan et al. Auto classification of product images based on complementary features and class descriptor [J]. Journal of Electronics and Information, 2010, 32(10): 2294–2300 (in Chinese).
Nguyen H V, Bai L. Compact binary patterns (CBP) with multiple patch classifiers for fast and accurate face recognition [J]. Lecture Notes in Computer Science, 2010, 6026: 187–198.
Zhao Z, Cai A. Combining multiple SVM classifiers for adult image recognition: Network infrastructure and digital content [C]//2nd IEEE International Conference on Network Infrastructure and Digital Content. Beijing, China: IEEE, 2010: 149–153.
Kittler J, Hatef M, Duin R PW, et al. On combining classifiers [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3): 226–239.
Lu X, Wang Y, Jain A K. Combining classifiers for face recognition [C]//Proceedings 2003 International Conference on Multimedia and Expo. Maryland, USA: IEEE, 1983: 13–16.
Lazebnik S, Schmid C, Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories [C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2006: 2169–2178.
Bosch A, Zisserman A, Munoz X. Representing shape with a spatial pyramid kernel [C]//Proceedings of the 6th ACM International Conference on Image and Video Retrieval. Amsterdam, the Netherlands: ACM Press, 2007: 401–408.
Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 7(24): 971–987.
Oliva A, Torralba A. Modeling the shape of the scene: A Holistic representation of the spatial envelope [J]. International Journal of Computer Vision, 2001, 42(3): 145–175.
Byun H. A survey on pattern recognition applications of support vector machines [J]. International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), 2003, 17(3): 459–486.
Xie X, Lu L, Jia M, et al. Mobile search with multimodal queries [J]. Proceedings of the IEEE, 2008, 96(4): 589–601.
Chang C, Lin C. LIBSVM: A library for support vector machines [J]. ACM Transactions on Intelligent Systems and Technology, 2001, 2(3): 1–27.
Wu T F, Lin C J, Weng R C. Probability estimates for multi-class classification by pairwise coupling [J]. Journal of Machine Learning Research, 2004, 12(5): 975–1005.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: the National Natural Science Foundation of China (No. 70890083) and the Project of National Innovation Fund for Technology Based Firms (No. 09c26222123243)
Rights and permissions
About this article
Cite this article
Jia, Sj., Kong, Xw. & Man, H. Automatic product image classification with multiple support vector machine classifiers. J. Shanghai Jiaotong Univ. (Sci.) 16, 391–394 (2011). https://doi.org/10.1007/s12204-011-1180-x
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12204-011-1180-x