Bayesian Online Learning of Corresponding Points of Objects with Sequential Monte Carlo
This paper presents an online method that learns the
corresponding points of an object from un-annotated grayscale images
containing instances of the object. In the first image being
processed, an ensemble of node points is automatically selected
which is matched in the subsequent images. A Bayesian posterior
distribution for the locations of the nodes in the images is formed.
The likelihood is formed from Gabor responses and the prior assumes
the mean shape of the node ensemble to be similar in a translation
and scale free space. An association model is applied for separating
the object nodes and background nodes. The posterior distribution is
sampled with Sequential Monte Carlo method. The matched object
nodes are inferred to be the corresponding points of the object
instances. The results show that our system matches the object nodes
as accurately as other methods that train the model with annotated
training images.
[1] L. Wiskott, J.-M. Fellous, N. Kruger, and C. von der Malsburg, "Face
recognition by elastic bunch graph matching," IEEE TPAMI, vol. 19, pp.
775-779, 1997.
[2] T. Cootes, G. Edwards, and C. Taylor, "Active appearance models," IEEE
TPAMI, vol. 23, no. 6, pp. 681-685, 2001.
[3] T. Tamminen and J. Lampinen, "Sequential Monte Carlo for Bayesian
matching of objects with occlusions," IEEE TPAMI, vol. 28, pp. 930-
941, 2006.
[4] J. Kamarainen, M. Hamouz, J. Kittler, P. Paalanen, J. Ilonen, and
A. Drobchenko, "Object localisation using generative probability model
for spatial constellation and local image features," in Proc. ICCV, 2007,
pp. 1-8.
[5] C. Doucet, J. de Freitas, and N. Gordon, Sequential Monte Carlo
Methods in Practice. Springer-Verlag, New York, 2001.
[6] M. Weber, M. Welling, and P. Perona, "Unsupervised learning of models
for recognition," in Proc. ECCV, 2000, pp. 18-32.
[7] R. Fergus, P. Perona, and A. Zisserman, "Object class recognition by
unsupervised scale-invariant learning," in Proc. CVPR, 2003, pp. 264-
271.
[8] L. Fei-Fei, R. Fergus, and P. Perona, "A Bayesian approach to unsupervised
one-shot learning of object categories," in Proc. ICCV, 2003, pp.
1134-1141.
[9] K. Mikolajczyk, B. Leibe, and B. Schiele, "Multiple object class
detection with a generative model," in Proc. CVPR, 2006, pp. 26-36.
[10] S. Lazebnik, C. Schmid, and J. Ponce, "A discriminative framework for
texture and object recognition using local image features," Lecture notes
in computer science, vol. 4170, p. 423, 2006.
[11] R. Fergus, P. Perona, and A. Zisserman, "A sparse object category model
for efficient learning and complete recognition," in Toward Category-
Level Object Recognition, ser. LNCS. Springer, 2007, vol. 4170, pp.
443-461.
[12] B. Leibe, A. Leonardis, and B. Schiele, "Combined object categorization
and segmentation with an implicit shape model," Workshop on Statistical
Learning in Computer Vision, ECCV, pp. 17-32, 2004.
[13] E. Borenstein, E. Sharon, and S. Ullman, "Combining top-down and
bottom-up segmentation," in Proc. CVPR Workshop, 2004, pp. 46-53.
[14] J. Winn and N. Jojic, "Locus: Learning object classes with unsupervised
segmentation," in Proc. ICCV, vol. 1, 2005.
[15] N. Ahuja and S. Todorovic, "Learning the taxonomy and models of
categories present in arbitrary images," in Proc. ICCV, 2007, pp. 1-8.
[16] L. Fei-Fei, R. Fergus, and P. Perona, "Learning generative visual models
from few training examples: An incremental Bayesian approach tested
on 101 object categories," Computer Vision and Image Understanding,
vol. 106, no. 1, pp. 59-70, 2007.
[17] J. Daugman, "Complete discrete 2-D Gabor transforms by neural
networks for imageanalysis and compression," IEEE Transactions on
Acoustics, Speech, and Signal Processing [see also IEEE Transactions
on Signal Processing], vol. 36, no. 7, pp. 1169-1179, 1988.
[18] R. Neal, "Probabilistic inference using Markov chain Monte Carlo
methods," Department of Computer Science, University of Toronto,
Tech. Rep., 1993.
[19] M. B. Stegmann, "Analysis and segmentation of face images using
point annotations and linear subspace techniques," Informatics and
Mathematical Modelling, Technical University of Denmark, Tech. Rep.,
2002.
[1] L. Wiskott, J.-M. Fellous, N. Kruger, and C. von der Malsburg, "Face
recognition by elastic bunch graph matching," IEEE TPAMI, vol. 19, pp.
775-779, 1997.
[2] T. Cootes, G. Edwards, and C. Taylor, "Active appearance models," IEEE
TPAMI, vol. 23, no. 6, pp. 681-685, 2001.
[3] T. Tamminen and J. Lampinen, "Sequential Monte Carlo for Bayesian
matching of objects with occlusions," IEEE TPAMI, vol. 28, pp. 930-
941, 2006.
[4] J. Kamarainen, M. Hamouz, J. Kittler, P. Paalanen, J. Ilonen, and
A. Drobchenko, "Object localisation using generative probability model
for spatial constellation and local image features," in Proc. ICCV, 2007,
pp. 1-8.
[5] C. Doucet, J. de Freitas, and N. Gordon, Sequential Monte Carlo
Methods in Practice. Springer-Verlag, New York, 2001.
[6] M. Weber, M. Welling, and P. Perona, "Unsupervised learning of models
for recognition," in Proc. ECCV, 2000, pp. 18-32.
[7] R. Fergus, P. Perona, and A. Zisserman, "Object class recognition by
unsupervised scale-invariant learning," in Proc. CVPR, 2003, pp. 264-
271.
[8] L. Fei-Fei, R. Fergus, and P. Perona, "A Bayesian approach to unsupervised
one-shot learning of object categories," in Proc. ICCV, 2003, pp.
1134-1141.
[9] K. Mikolajczyk, B. Leibe, and B. Schiele, "Multiple object class
detection with a generative model," in Proc. CVPR, 2006, pp. 26-36.
[10] S. Lazebnik, C. Schmid, and J. Ponce, "A discriminative framework for
texture and object recognition using local image features," Lecture notes
in computer science, vol. 4170, p. 423, 2006.
[11] R. Fergus, P. Perona, and A. Zisserman, "A sparse object category model
for efficient learning and complete recognition," in Toward Category-
Level Object Recognition, ser. LNCS. Springer, 2007, vol. 4170, pp.
443-461.
[12] B. Leibe, A. Leonardis, and B. Schiele, "Combined object categorization
and segmentation with an implicit shape model," Workshop on Statistical
Learning in Computer Vision, ECCV, pp. 17-32, 2004.
[13] E. Borenstein, E. Sharon, and S. Ullman, "Combining top-down and
bottom-up segmentation," in Proc. CVPR Workshop, 2004, pp. 46-53.
[14] J. Winn and N. Jojic, "Locus: Learning object classes with unsupervised
segmentation," in Proc. ICCV, vol. 1, 2005.
[15] N. Ahuja and S. Todorovic, "Learning the taxonomy and models of
categories present in arbitrary images," in Proc. ICCV, 2007, pp. 1-8.
[16] L. Fei-Fei, R. Fergus, and P. Perona, "Learning generative visual models
from few training examples: An incremental Bayesian approach tested
on 101 object categories," Computer Vision and Image Understanding,
vol. 106, no. 1, pp. 59-70, 2007.
[17] J. Daugman, "Complete discrete 2-D Gabor transforms by neural
networks for imageanalysis and compression," IEEE Transactions on
Acoustics, Speech, and Signal Processing [see also IEEE Transactions
on Signal Processing], vol. 36, no. 7, pp. 1169-1179, 1988.
[18] R. Neal, "Probabilistic inference using Markov chain Monte Carlo
methods," Department of Computer Science, University of Toronto,
Tech. Rep., 1993.
[19] M. B. Stegmann, "Analysis and segmentation of face images using
point annotations and linear subspace techniques," Informatics and
Mathematical Modelling, Technical University of Denmark, Tech. Rep.,
2002.
@article{"International Journal of Information, Control and Computer Sciences:61475", author = "Miika Toivanen and Jouko Lampinen", title = "Bayesian Online Learning of Corresponding Points of Objects with Sequential Monte Carlo", abstract = "This paper presents an online method that learns the
corresponding points of an object from un-annotated grayscale images
containing instances of the object. In the first image being
processed, an ensemble of node points is automatically selected
which is matched in the subsequent images. A Bayesian posterior
distribution for the locations of the nodes in the images is formed.
The likelihood is formed from Gabor responses and the prior assumes
the mean shape of the node ensemble to be similar in a translation
and scale free space. An association model is applied for separating
the object nodes and background nodes. The posterior distribution is
sampled with Sequential Monte Carlo method. The matched object
nodes are inferred to be the corresponding points of the object
instances. The results show that our system matches the object nodes
as accurately as other methods that train the model with annotated
training images.", keywords = "Bayesian modeling, Gabor filters, Online learning, Sequential Monte Carlo.", volume = "3", number = "12", pages = "2900-7", }