© The Institution of Engineering and Technology
This study is about object matching, that is, a problem of locating the corresponding points of an object in an image. Conventional approaches to object matching are batch methods, meaning that the methods first learn the object model from a training set of example images that contain instances of the object, and then use the learned object model to match instances of the same object (or object class) in unseen test images. Such batch learning often leads to computationally heavy learning, at least when the images are incorporated sequentially into the system and large memory requirements. In computer vision, little work has been done in developing incremental object learners. Especially, an incremental object-matching method has – to the best knowledge of the authors – never been introduced. In this paper, the authors present such a method. Our technique finds the corresponding points of similar object instances, appearing in natural greyscale images with arbitrary location, scale and orientation, by processing the images sequentially. The approach is Bayesian and combines the shape and appearance of the corresponding points into the posterior distribution for the location of them. The posterior distribution is recursively sampled with particle filters to locate the most probable corresponding point sets in the image being processed. The results indicate that the matched corresponding points can be used in forming a representation of the object with which instances of the object in novel test images are successfully detected.
References
-
-
1)
-
Kamarainen, J., Hamouz, M., Kittler, J., Paalanen, P., Ilonen, J., Drobchenko, A.: `Object localisation using generative probability model for spatial constellation and local image features', Proc. ICCV, 2007, p. 1–8.
-
2)
-
Weber, M., Welling, M., Perona, P.: `Unsupervised learning of models for recognition', Proc. ECCV, 2000, p. 18–32.
-
3)
-
Y. Bar-Shalom ,
X.R. Li
.
(1995)
Multitarget–multisensor tracking: principles and techniques.
-
4)
-
Fei-Fei, L., Fergus, R., Perona, P.: `A Bayesian approach to unsupervised one-shot learning of object categories', Proc. ICCV, 2003, p. 1134–1141.
-
5)
-
A. Opelt ,
A. Pinz ,
M. Fussenegger ,
P. Auer
.
Generic object recognition with boosting.
IEEE Trans. Pattern Anal. Mach. Intell.
,
3 ,
416 -
431
-
6)
-
Winn, J., Jojic, N.: `LOCUS: learning object classes with unsupervised segmentation', Proc. ICCV, 2005, 1, p. 756–763.
-
7)
-
A. Doucet ,
N. de Freitas ,
N. Gordon
.
(2001)
Sequential Monte Carlo methods in practice.
-
8)
-
T. Serre ,
L. Wolf ,
S. Bileschi ,
M. Riesenhuber ,
T. Poggio
.
Robust object recognition with cortex-like mechanisms.
IEEE Trans. Pattern Anal. Mach. Intell.
,
3 ,
411 -
426
-
9)
-
L. Wiskott ,
J.-M. Fellous ,
N. Kuiger ,
C. Von Der Malsburg
.
Face recognition by elastic bunch graph matching.
IEEE Trans. Pattern Anal. Mach. Intell.
,
7 ,
775 -
779
-
10)
-
A. Gelman ,
J.B. Carlin ,
H.S. Stern ,
D.B. Rubin
.
(2004)
Bayesian data analysis.
-
11)
-
Borenstein, E., Sharon, E., Ullman, S.: `Combining top-down and bottom-up segmentation', Proc. CVPR Workshop, 2004, p. 46–53.
-
12)
-
J. Zhang ,
M. Marszalek ,
S. Lazebnik ,
C. Schmid
.
Local features and kernels for classification of texture and object categories: a comprehensive study.
Int. J. Comput. Vis.
,
2 ,
213 -
238
-
13)
-
S. Escalera ,
O. Pujol ,
P. Radeva
.
Boosted landmarks of contextual descriptors and forest-ECOC: a novel framework to detect and classify objects in cluttered scenes.
Pattern Recognit. Lett
,
13 ,
1759 -
1768
-
14)
-
Amores, J., Sebe, N., Radeva, P.: `Fast spatial pattern discovery integrating boosting with constellations of contextual descriptors', Proc. CVPR, 2005, 2, p. 769–775.
-
15)
-
T. Tamminen ,
J. Lampinen
.
Sequential Monte Carlo for Bayesian matching of objects with occlusions.
IEEE Trans. Pattern Anal. Mach. Intell.
,
930 -
941
-
16)
-
P. Craven ,
G. Wahba
.
Smoothing noisy data with spline functions.
Numer. Math
,
4 ,
377 -
403
-
17)
-
M.J.L. Orr
.
Introduction to radial basis function networks.
-
18)
-
K. Koeser ,
C. Perwass ,
G. Sommer
.
Dense optic flow with a Bayesian occlusion model.
Lect. Notes Comput. Sci.
,
127 -
139
-
19)
-
J. Daugman
.
Complete discrete 2-D Gabor transforms by neural networks for imageanalysis and compression.
IEEE Trans. Acoust., Speech Signal Process
,
7 ,
1169 -
1179
-
20)
-
Fergus, R., Perona, P., Zisserman, A.: `A sparse object category model for efficient learning and complete recognition', Toward category-level object recognition, p. 443–461, (LNCS, 4170) (Springer, 2007).
-
21)
-
T.F. Cootes ,
G.J. Edwards ,
C.J. Taylor
.
Active appearance models.
IEEE Trans. Pattern Anal. Mach. Intell.
,
6 ,
681 -
685
-
22)
-
O. Cappe ,
A. Guillin ,
J.M. Marin ,
C.P. Robert
.
Population Monte Carlo.
J. Comput. Graph. Statist.
,
4 ,
907 -
929
-
23)
-
M. Toivanen ,
J. Lampinen
.
Bayesian online learning of corresponding points of objects with sequential Monte Carlo.
Int. J. Comput. Intell
,
4 ,
318 -
324
-
24)
-
Shotton, J., Blake, A., Cipolla, R.: `Contour-based learning for object detection', Proc. ICCV, 2005, 1, p. 503–510.
-
25)
-
J. Liu ,
R. Chen ,
T. Logvinenko ,
C.A. Doucet ,
J. de Freitas ,
N. Gordon
.
(2001)
A theoretical framework for sequential importance sampling with resampling, Sequential Monte Carlo methods in practice.
-
26)
-
Willamowski, J., Arregui, D., Csurka, G., Dance, C.R., Fan, L.: `Categorizing nine visual classes using local appearance descriptors', ICPR Workshop on Learning for Adaptable Visual Systems, 2004, p. 21–31.
-
27)
-
Toivanen, M., Lampinen, J.: `Incremental Bayesian learning of feature points from natural images', Proc. CVPR Workshops, 2009, p. 39–46.
-
28)
-
Toivanen, M., Lampinen, J.: `Incremental object matching with Bayesian methods and particle filters', Proc. Digital Image Computing: techniques and Applications, 2009, p. 111–118.
-
29)
-
S. Lazebnik ,
C. Schmid ,
J. Ponce
.
A discriminative framework for texture and object recognition using local image features.
Lect. Notes Comput. Sci.
,
423 -
442
-
30)
-
F.F. Li ,
R. Fergus ,
P. Perona
.
Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories.
Comput. Vis. Image Underst.
,
1 ,
59 -
70
-
31)
-
Mikolajczyk, K., Leibe, B., Schiele, B.: `Multiple object class detection with a generative model', Proc. CVPR, 2006, p. 26–36.
-
32)
-
Fergus, R., Perona, P., Zisserman, A.: `Object class recognition by unsupervised scale-invariant learning', Proc. CVPR, 2003, p. 264–271.
-
33)
-
Lazebnik, S., Schmid, C., Ponce, J.: `Semi-local affine parts for object recognition', Proc. BMVC, 2004, 2, p. 959–968.
-
34)
-
A.D. Holub ,
M. Welling ,
P. Perona
.
Hybrid generative-discriminative visual categorization.
Int. J. Comput. Vis
,
1 ,
239 -
258
-
35)
-
Wolf, L., Martin, I.: `Robust boosting for learning from few examples', Proc. CVPR, 2005, p. 359–364.
-
36)
-
Ahuja, N., Todorovic, S.: `Learning the taxonomy and models of categories present in arbitrary images', Proc. ICCV;, 2007, p. 1–8.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2010.0030
Related content
content/journals/10.1049/iet-cvi.2010.0030
pub_keyword,iet_inspecKeyword,pub_concept
6
6