Abstract
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors extracted from the images. In this paper we present a novel method to build such a codebook with class representative vectors. This method, coined Cluster Precision Maximization (CPM), is based on a new measure of the cluster precision and on an optimization procedure that leads any clustering algorithm towards class representative visual words. We compare our procedure with other measures of cluster precision and present the integration of a Reciprocal Nearest Neighbor (RNN) clustering algorithm in the CPM method. In the experiments, on a subset of the the Caltech101 database, we analyze several vocabularies obtained with different local descriptors and different clustering algorithms, and we show that the vocabularies obtained with the CPM process perform best in a category-level object recognition system using a Support Vector Machine (SVM).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proceedings of the ECCV (2004)
Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Proceedings of the CVPR (2008)
van de Sande, K., Gevers, T., Snoek, C.: Evaluation of color descriptors for object and scene recognition. In: Proceedings of the CVPR (2008)
Everingham, M., et al.: The PASCAL voc 2008 Results (2008), http://www.pascal-network.org/challenges/VOC/voc2008/workshop/index.html
Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: A survey. Foundations and Trends in Computer Graphics and Vision 3(3), 177–280 (2008)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on PAMI 27(10), 1615–1630 (2005)
Sivic, J., Zisserman, A.: Video data mining using configurations of viewpoint invariant regions. In: Proceedings of the CVPR, pp. 488–495 (2004)
Quack, T., Ferrari, V., Leibe, B., Van Gool, L.: Efficient mining of frequent and distinctive feature configurations. In: Proceedings of the ICCV (2007)
Yuan, J., Wu, Y.: Context-aware clustering. In: Proceedings of the CVPR (2008)
Lazebnik, S., Schmid, C., Ponce, J.: Semi-local affine parts for object recognition. In: Proceedings of the BMVC (2004)
Leibe, B., Ettlin, A., Schiele, B.: Learning semantic object parts for object categorization. Image and Vision Computing 26(1), 15–26 (2008)
Perronnin, P., Dance, C., Csurka, G., Bressan, M.: Adapted vocabularies for generic visual categorization. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 464–475. Springer, Heidelberg (2006)
Winn, J., Criminisi, A., Minka, A.: Object categorization by learned universal visual dictionary. In: Proceedings of the ICCV (2005)
Moosmann, F., Triggs, B., Jurie, F.: Fast discriminative visual codebooks using randomized clustering forests. In: Advances in NIPS (2006)
Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: Proceedings of the CVPR (2007)
Mikolajczyk, K., Leibe, B., Schiele, B.: Local features for object class recognition. In: Proceedings of the ICCV (2005)
Stark, M., Schiele, B.: How good are local features for classes of geometric objects. In: Proceedings of the ICCV, pp. 1–8 (2007)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Transactions on PAMI 24(24), 509–522 (2002)
Leibe, B., Mikolajczyk, K., Schiele, B.: Efficient clustering and matching for object class recognition. In: Proceedings of the BMVC (2006)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: Proceedings of the CVPR (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
López Sastre, R.J., Tuytelaars, T., Maldonado Bascón, S. (2009). Class Representative Visual Words for Category-Level Object Recognition. In: Araujo, H., Mendonça, A.M., Pinho, A.J., Torres, M.I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2009. Lecture Notes in Computer Science, vol 5524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02172-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-02172-5_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02171-8
Online ISBN: 978-3-642-02172-5
eBook Packages: Computer ScienceComputer Science (R0)