Abstract
This paper describes a new method for acquiring object categories by searching images on the Internet. An unsupervised method is proposed that, starting from a set of objects extracted from the Internet images automatically fetched for a given category name, selects a subset of objects suitable for building a model of the category. The method is based on repeated k-means clustering. Object relevance scoring is based on properties of the clusters in which they are placed. The approach is evaluated on generic categories (i.e. those usually referenced through common nouns). We demonstrate that the proposed approach significantly improves the quality of the training object collections.
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
Preview
Unable to display preview. Download preview PDF.
References
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) Challenge. International Journal of Computer Vision 88(2), 303–338 (2010)
Geusebroek, J.M., Burghouts, G.J., Smeulders, A.W.M.: The Amsterdam library of object images. Int. J. Comput. Vision 61(1), 103–112 (2005)
Seabra Lopes, L., Chauhan, A.: Open-Ended Category Learning for Language Acquisition. Connection Science 20(4), 277–297 (2008)
Wnuk, K., Soatto, S.: Filtering internet image search results towards keyword based category recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (2008)
Vijayanarasimhan, S., Grauman, K.: Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization. In: Proc. CVPR 2008 (2008)
Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from internet image searches. Proc. IEEE 98(8), 1453–1466 (2010)
Pereira, R., Seabra Lopes, L., Silva, A.: Semantic Image Search and Subset Selection for Classifier Training in Object Recognition. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol. 5816, pp. 338–349. Springer, Heidelberg (2009)
Pereira, R., Seabra Lopes, L.: Learning visual object categories with global descriptors and local features. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol. 5816, pp. 225–236. Springer, Heidelberg (2009)
Antunes, M., Lopes, L.S.: Contour-based object extraction and clutter removal for semantic vision. In: Kamel, M., Campilho, A. (eds.) ICIAR 2013. LNCS, vol. 7950, pp. 170–180. Springer, Heidelberg (2013)
Lloyd, S.P.: Least squares quantization in PCM. Bell Telephone Laboratories Paper, Murray Hill, NJ (1957); published later in. IEEE Transactions on Information Theory 28(2), 129–137 (1982)
Arthur, D., Vassilvitskii, S.: k-means++: the Advantages of Careful Seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete algorithms, SODA 2007, pp. 1027–1035. Society for Industrial and Applied Mathematics (2007)
Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice-Hall (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Antunes, M., Lopes, L.S. (2013). Unsupervised Internet-Based Category Learning for Object Recognition. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2013. Lecture Notes in Computer Science, vol 7950. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39094-4_88
Download citation
DOI: https://doi.org/10.1007/978-3-642-39094-4_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39093-7
Online ISBN: 978-3-642-39094-4
eBook Packages: Computer ScienceComputer Science (R0)