Abstract
We develop a novel approach to view-invariant recognition and apply it to the task of recognizing face images under widely separated viewing directions. Our main contribution is a novel object representation scheme using ‘extended fragments’ that enables us to achieve a high level of recognition performance and generalization across a wide range of viewing conditions. Extended fragments are equivalence classes of image fragments that represent informative object parts under different viewing conditions. They are extracted automatically from short video sequences during learning. Using this representation, the scheme is unique in its ability to generalize from a single view of a novel object and compensate for a significant change in viewing direction without using 3D information. As a result, novel objects can be recognized from viewing directions from which they were not seen in the past. Experiments demonstrate that the scheme achieves significantly better generalization and recognition performance than previously used methods.
Chapter PDF
References
Mundy, J., Zisserman, A.: Geometric Invariance in Computer Vision. The MIT press, Cambridge (1992)
Tuytelaars, T., Gool, L.V.: Wide baseline stereo matching based on local, affinely invariant regions. In: British Machine Vision Conference, pp. 412–425 (2000)
Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)
Wallraven, C., Bülthoff, H.H.: Automatic acquisition of exemplar-based representations for recognition from image sequences. In: CVPR 2001 - Workshop on Models vs. Exemplars (2001)
Beymer, D.J.: Face recognition under varying pose. Technical Report AIM-1461, MIT Artificial Intelligence Lab (1993)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Rockwood, A. (ed.) Siggraph 1999, Computer Graphics Proceedings, Los Angeles, pp. 187–194. Addison Wesley Longman, Amsterdam (1999)
Nagashima, Y., Agawa, H., Kishino, F.: 3D face model reproduction method using multi view images. In: Proceedings of the SPIE, Visual Communications and Image Processing 1991, vol. 1606, pp. 566–573 (1991)
Lowe, D.G.: Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence 31, 355–395 (1987)
Wiskott, L., Fellous, J.M., Krüger, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. In: Jain, L.C., Halici, U., Hayashi, I., Lee, S.B. (eds.) Intelligent Biometric Techniques in Fingerprint and Face Recognition, pp. 355–396. CRC Press, Boca Raton (1999)
Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998)
Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience 3, 71–86 (1991)
Murase, H., Nayar, S.: Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision 14, 5–24 (1995)
Pentland, A., Moghaddam, B., Starner, T.: View-based and modular eigenspaces for face recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA (1994)
Sali, E., Ullman, S.: Combining class-specific fragments for object recognition. In: British Machine Vision Conference, pp. 203–213 (1999)
Ullman, S., Vidal-Naquet, M., Sali, E.: Visual features of intermediate complexity and their use in classification. Nature Neuroscience 5, 682–687 (2002)
Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–127. Springer, Heidelberg (2002)
Phillips, P.J., Wechsler, H., Huang, J., Rauss, P.: The FERET database and evaluation procedure for face recognition algorithms. Image and Vision Computing 16, 295–306 (1998)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical Report CMU-CS-91-132, Carnegie Mellon University (1991)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, Chichester (1991)
Amit, Y., Geman, D.: Shape quantization and recognition with randomized trees. Neural Computation 9, 1545–1588 (1997)
Mel, B.W.: SEEMORE: Combining color, shape and texture histogramming in a neurally-inspired approach to visual object recognition. Neural Computation 9, 777–804 (1997)
Weber, M., Welling, M., Perona, P.: Towards automatic discovery of object categories. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 101–109 (2002)
Basri, R., Jacobs, D.W.: Lambertian reflectance and linear subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 218–233 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bart, E., Byvatov, E., Ullman, S. (2004). View-Invariant Recognition Using Corresponding Object Fragments. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive