Abstract
In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class recognition systems. Currently, many state-of-the-art approaches have models involving very restrictive priors in terms of the number of local features and their spatial relations. The adoption of such priors in those models are necessary for simplifying both the learning and inference tasks. Also, most of the state-of-the-art learning approaches are semi-supervised batch processes, which considerably reduce their suitability in dynamic environments, where unannotated new images are continuously presented to the learning system. In this work we propose: 1) a new model representation that has a less restrictive prior on the geometry and number of local features, where the geometry of each local feature is influenced by its k closest neighbors and models may contain hundreds of features; and 2) a novel unsupervised on-line learning algorithm that is capable of estimating the model parameters efficiently and accurately. We implement a visual class recognition system using the new model and learning method proposed here, and demonstrate that our system produces competitive classification and localization results compared to state-of-the-art methods. Moreover, we show that the learning algorithm is able to model not only classes with consistent texture (e.g., faces), but also classes with shape only (e.g., leaves), classes with a common shape but with a great variability in terms of internal texture (e.g., cups), and classes of flexible objects (e.g., snake).
Chapter PDF
References
Amit, Y., Geman, D.: A computational model for visual selection. Neural Computation 11, 1691–1715 (1999)
Arya, S., Mount, D.M., Netanyahu, N.S., Silverman, R., Wu, A.Y.: An optimal algorithm for approximate nearest neighbor searching. Journal of the ACM 45, 891–923 (1998)
Bouchard, G., Triggs, B.: Hierarchical part-based visual object categorization. In: CVPR (2005)
Burl, M., Weber, M., Perona, P.: A probabilistic approach to object recognition using local photometry and global geometry. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, p. 628. Springer, Heidelberg (1998)
Carneiro, G., Jepson, A.: Multi-scale local phase features. In: CVPR (2003)
Carneiro, G., Jepson, A.: Flexible spatial models for grouping local image features. In: CVPR (2004)
Carneiro, G., Jepson, A.: The distinctiveness, detectability, and robustness of local image features. In: CVPR (2005)
Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical models. In: CVPR (2005)
Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: ECCV Workshop on Statistical Learning in Computer Vision (2004)
Everingham, M., Van Gool, L., Williams, C., Zisserman, A.: Pascal Visual Object Classes Challenge Results (2005), http://www.pascal-network.org/challenges/VOC/voc/results_050405.pdf
Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. IJCV 61(1), 55–79 (2005)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)
Fergus, R., Perona, P., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: CVPR (2005)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous object recognition and segmentation by image exploration. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 40–54. Springer, Heidelberg (2004)
Lazebnik, S., Schmid, C., Ponce, J.: Semi-local affine parts for object recognition. In: BMVC (2004)
Liebe, B., Schiele, B.: Interleaved object categorization and segmentation. In: BMVC (2003)
Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999)
Moreels, P., Maire, M., Perona, P.: Recognition by probabilistic hypothesis construction. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 55–68. Springer, Heidelberg (2004)
Ramanan, D., Forsyth, D., Barnard, K.: Detecting, localizing, and recovering kinematics of textured animals. In: CVPR (2004)
Vasconcelos, N.: Bayesian models for visual information retrieval. PhD thesis, Massachusetts Institute of Technology (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carneiro, G., Lowe, D. (2006). Sparse Flexible Models of Local Features. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3953. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744078_3
Download citation
DOI: https://doi.org/10.1007/11744078_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33836-9
Online ISBN: 978-3-540-33837-6
eBook Packages: Computer ScienceComputer Science (R0)