nips nips2004 nips2004-40 nips2004-40-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Pierre Moreels, Pietro Perona
Abstract: A generative probabilistic model for objects in images is presented. An object consists of a constellation of features. Feature appearance and pose are modeled probabilistically. Scene images are generated by drawing a set of objects from a given database, with random clutter sprinkled on the remaining image surface. Occlusion is allowed. We study the case where features from the same object share a common reference frame. Moreover, parameters for shape and appearance densities are shared across features. This is to be contrasted with previous work on probabilistic ‘constellation’ models where features depend on each other, and each feature and model have different pose and appearance statistics [1, 2]. These two differences allow us to build models containing hundreds of features, as well as to train each model from a single example. Our model may also be thought of as a probabilistic revisitation of Lowe’s model [3, 4]. We propose an efficient entropy-minimization inference algorithm that constructs the best interpretation of a scene as a collection of objects and clutter. We test our ideas with experiments on two image databases. We compare with Lowe’s algorithm and demonstrate better performance, in particular in presence of large amounts of background clutter.
[1] M. Weber, M. Welling and P. Perona, “Unsupervised Learning of Models for Recognition”, Proc. Europ. Conf. Comp. Vis., 2000.
[2] R. Fergus, P. Perona, A. Zisserman, “Object Class Recognition by Unsupervised Scale-invariant Learning”, IEEE. Conf. on Comp. Vis. and Patt. Recog., 2003.
[3] D.G. Lowe, “Object Recognition from Local Scale-invariant Features”, ICCV,1999
[4] D.G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints”, Int. J. Comp. Vis., 60(2), pp. 91-110, 2004.
[5] G. Carneiro and A. Jepson “Flexible Spatial Models for Grouping Local Image Features”, IEEE. Conf. on Comp. Vis. and Patt. Recog., 2004.
[6] I. Rigoutsos and R. Hummel “A Bayesian Approach to Model Matching with Geometric Hashing”, CVIU, 62(1), pp. 11-26, 1995.
[7] W.E.L. Grimson and D.P. Huttenlocher, “On the Sensitivity of Geometric Hashing”, ICCV, 1990
[8] H. Rowley, S. Baluja, T. Kanade, “Neural Network-based Face Detection”, IEEE. Trans. Patt. Anal. Mach. Int., 20(1):pp. 23-38, 1998.
[9] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features”, Proc. IEEE Conf. Comp. Vis. Patt. Recog., 2001.
[10] L. Fei-Fei, R. Fergus, P. Perona. “Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories” CVPR, 2004.
[11] P. Moreels, M. Maire, P. Perona, ’Recognition by Probabilistic Hypothesis Construction’, Proc. 8th Europ. Conf. Comp. Vision, Prague, Czech Republic, pp.55-68, 2004
[12] T. Lindeberg, “Scale-space Theory: a Basic Tool for Analising Structures at Different Scales”, J. Appl. Stat., 21(2), pp.225-270, 1994.
[13] A.R. Pope and D.G. Lowe, “Probabilistic Models of Appearance for 3-D Object Recognition”, Int. J. Comp. Vis., 40(2), pp. 149-167, 2000.
[14] D. Geman and B. Jedynak, “An Active Testing Model for Tracking Roads in Satellite Images”, IEEE. Trans. Patt. Anal. Mach. Int.,18(1) pp. 1 - 14,1996
[15] C. Schmid, R. Mohr, C. Bauckhage”, “Comparing and Evaluating Interest Points”, Proc. of 6th Int. Conf. Comp. Vis., Bombay, India, 1998.