Abstract
We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of corresponding geometric blur point descriptors as well as the geometric distortion between pairs of corresponding feature points. The algorithm handles outliers, and thus enables matching of exemplars to query images in the presence of occlusion and clutter. Given the correspondences, we estimate an aligning transform, typically a regularized thin plate spline, resulting in a dense correspondence between the two shapes. Object recognition is handled in a nearest neighbor framework where the distance between exemplar and query is the matching cost between corresponding points. We show results on two datasets. One is the Caltech 101 dataset (Li, Fergus and Perona), a challenging dataset with large intraclass variation. Our approach yields a 45% correct classification rate in addition to localization. We also show results for localizing frontal and profile faces that are comparable to special purpose approaches tuned to faces.
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
Amit, Y., Geman, D., Wilder, K.: Joint induction of shape features and tree classifiers. IEEE Trans. PAMI 19(11), 1300–1305 (1997)
Belongie, S., Malik, J., Puzicha, J.: Matching shapes. In: Proc. 8th Int. Conf. Computer Vision, vol.1, pp. 454–461 (2001)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. PAMI 24(4), 509–522 (2002)
Berg, A.C.: Shape Matching and Object Recognition. Ph.D thesis, U.C. Berkeley (December 2005)
Berg, A.C., Malik, J.: Geometric blur for template matching. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 607–614 (2001)
Berg, T.L., Berg, A.C., Edwards, J., Maire, M., White, R., Teh, Y.W., Learned-Miller, E., Forsyth, D.A.: Names and faces in the news. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 848–854 (2004)
Caltech 101 dataset, http://www.vision.caltech.edu/feifeili/101_ObjectCategories
Chui, H., Rangarajan, A.: A new point matching algorithm for non-rigid registration. Comp. Vision and Image Underst. 89, 114–141 (2003)
Fei-Fei, L., Fergus, R., Perona, P.: A bayesian approach to unsupervised one-shot learning of object categories. In: Proc. 9th Int. Conf. Computer Vision, pp. 1134–1141 (2003)
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: Workshop on Generative-Model Based Vision (2004)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 264–271 (2003)
Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. IEEE Trans. Computers C-22(1), 67–92 (1973)
Gavrila, D., Philomin, V.: Real-time object detection for smart vehicles. In: Proc. 7th Int. Conf. Computer Vision, pp. 87–93 (1999)
Grenander, U., Chow, Y., Keenan, D.M.: HANDS: A Pattern Theoretic Study Of Biological Shapes. Springer, Heidelberg (1991)
Holub, A., Welling, M., Perona, P.: Combining generative models and fisher kernels for object recognition. In: Proc. 10th Int. Conf. Computer Vision, pp. 136–143 (2005)
Huttenlocher, D.P., Klanderman, G., Rucklidge, W.: Comparing images using the Hausdorff distance. IEEE Trans. PAMI 15(9), 850–863 (1993)
Lades, M., Vorbrüggen, C.C., Buhmann, J., Lange, J., von der Malsburg, C., Wurtz, R.P., Konen, W.: Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. Computers 42(3), 300–311 (1993)
Lamdan, Y., Schwartz, J.T., Wolfson, H.J.: Affine invariant model-based object recognition. IEEE Trans. Robotics and Automation 6, 578–589 (1990)
Leung, T.K., Burl, M.C., Perona, P.: Finding faces in cluttered scenes using random labeled graph matching. In: Proc. 5th Int. Conf. Computer Vision, pp. 637–644 (1995)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. 7th Int. Conf. Computer Vision, pp. 1150–1157 (1999)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision 60(2), 91–110 (2004)
Maciel, J., Costeira, J.: A global solution to sparse correspondence problems. IEEE Trans. PAMI 25(2), 187–199 (2003)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. PAMI 26(5), 530–549 (2004)
Mikolajczyk, K.: Detection of local features invariant to affines transformations. Ph.D thesis, INPG (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 257–263 (2003)
Mori, G., Belongie, S., Malik, J.: Shape contexts enable efficient retrieval of similar shapes. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., vol. 1, pp. 723–730 (2001)
Morrone, M., Burr, D.: Feature detection in human vision: A phase dependent energy model. Proc. Royal Soc. of London B 235, 221–245 (1988)
Powell, M.J.D.: A thin plate spline method for mapping curves into curves in two dimensions. In: CTAC, Melbourne, Australia (1995)
Rangarajan, A., Chui, H., Mjolsness, E.: A relationship between spline-based deformable models and weighted graphs in non-rigid matching. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., vol.1, pp. 897–904 (December 2001)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using affine-invariant patches and multi-view spatial constraints. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp.II: 272–275 (2003)
Schneiderman, H., Kanade, T.: A statistical method for 3d object detection applied to faces and cars. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 746–751 (2000)
Schneiderman, H.: Feature-centric evaluation for efficient cascaded object detection. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 29–36 (2004)
Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Trans. PAMI 19(5), 530–535 (1997)
Thompson, D.A.W.: On Growth and Form. Dover, Mineola (1917)
Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing features: efficient boosting procedures for multiclass object detection. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., pp. 762–769 (2004)
Ullman, S., Vidal-Naquet, M., Sali, E.: Visual features of intermediate complexity and their use in classification. Nat. Neur. 13, 682–687 (2002)
Viola, P., Jones, M.: Robust real-time object detection. In: 2nd Intl. Workshop on Statistical and Computational Theories of Vision (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Berg, A.C., Malik, J. (2006). Shape Matching and Object Recognition. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds) Toward Category-Level Object Recognition. Lecture Notes in Computer Science, vol 4170. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11957959_25
Download citation
DOI: https://doi.org/10.1007/11957959_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68794-8
Online ISBN: 978-3-540-68795-5
eBook Packages: Computer ScienceComputer Science (R0)