Abstract
We describe how to model the appearance of an object using multiple views, learn such a model from training images, and recognize objects with it. The model uses probability distributions to characterize the significance, position, and intrinsic measurements of various discrete features of appearance; it also describes topological relations among features. The features and their distributions are learned from training images depicting the modeled object. A matching procedure, combining qualities of both alignment and graph subisomorphism methods, uses feature uncertainty information recorded by the model to guide the search for a match between model and image. Experiments show the method capable of learning to recognize complex objects in cluttered images, acquiring models that represent those objects using relatively few views.
Preview
Unable to display preview. Download preview PDF.
References
N. Ayache, O.D. Faugeras. HYPER: A new approach for the recognition and positioning of two-dimensional objects. IEEE Trans. Patt. Anal. Mach. Intell. PAMI-8:44–54, 1986.
J.S. Beis, D.G. Lowe. Learning indexing functions for 3-D model-based object recognition. In Proc. Conf. Computer Vision and Patt. Recognit., 275–280, 1994.
G.J. Bierman. Factorization Methods for Discrete Sequential Estimation. Academic Press, 1977.
T.M. Breuel. Fast recognition using adaptive subdivisions of transformation space. In Proc. Conf. Computer Vision and Patt. Recognit., 445–451, 1992.
J.B. Burns, E.M. Riseman. Matching complex images to multiple 3D objects using view description networks. In Proc. Conf. Computer Vision and Patt. Recognit., 328–334, 1992.
O.I. Camps, L.G. Shapiro, R.M. Haralick. Object recognition using prediction and probabilistic matching. In Proc. of the IEEE/RSJ Int. Conf. on Intell. Robots and Systems, 1044–1052, July 1992.
T. A. Cass. Polynomial-time object recognition in the presence of clutter, occlusion, and uncertainty. In Proc. European Conf. on Computer Vision, 834–842, 1992.
C.H. Chen, P.G. Mulgaonkar. Automatic vision programming. CVGIP: Image Understanding 55:170–183, 1992.
J.H. Connell, M. Brady. Generating and generalizing models of visual objects. Artificial Intell. 31:159–183, 1987.
D.H. Fisher. Knowledge acquisition via incremental conceptual clustering. Machine Learning 2:139–172, 1987.
P. Gros. Matching and clustering: Two steps towards automatic object model generation in computer vision. In Proc. AAAI Fall Symp.: Machine Learning in Computer Vision, AAAI Press, 1993.
Y. Hel-Or, M. Werman. Pose estimation by fusing noisy data of different dimensions. IEEE Trans. Patt. Anal. Mach. Intell. 17:195–201, 1995.
D.G. Lowe. The viewpoint consistency constraint. Int. J. Computer Vision 1:57–72, 1987.
H. Murase, S.K. Nayar. Learning and recognition of 3-D objects from brightness images. In Proc. AAAI Fall Symp.: Machine Learning in Computer Vision, 25–29, AAAI Press, 1993.
A.R. Pope, D.G. Lowe. Learning object recognition models from images. In Proc. Int. Conf. Computer Vision, 296–301, 1993.
A.R. Pope. Learning to Recognize Objects in Images: Acquiring and Using Probabilistic Models of Appearance. Ph.D. thesis, Univ. of British Columbia, 1995. WWW http://www.cs.ubc.ca/spider/pope/Thesis.html.
I. Rigoutsos, R. Hummel. Distributed Bayesian object recognition. In Proc. Conf. Computer Vision and Patt. Recognit., 180–186, 1993.
J. Rissanen. A universal prior for integers and estimation by minimum description length. Annals of Statistics 11:416–431, 1983.
K.B. Sarachik, W.E.L. Grimson. Gaussian error models for object recognition. In Proc. Conf. Computer Vision and Patt. Recognit., 400–406, 1993.
M. Seibert, A.M. Waxman. Adaptive 3-D object recognition from multiple views. IEEE Trans. Patt. Anal. Mach. Intell. 14:107–124, 1992.
M.A. Turk, A.P. Pentland. Face recognition using eigenfaces. In Proc. Conf. Computer Vision and Patt. Recognit., 586–591, 1991.
S. van Huffel, J. Vandewalle. The Total Least Squares Problem: Computational Aspects and Analysis. SIAM, 1991.
W.M. Wells III. Statistical Object Recognition. Ph.D. thesis, MIT, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pope, A.R., Lowe, D.G. (1996). Learning appearance models for object recognition. In: Ponce, J., Zisserman, A., Hebert, M. (eds) Object Representation in Computer Vision II. ORCV 1996. Lecture Notes in Computer Science, vol 1144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61750-7_30
Download citation
DOI: https://doi.org/10.1007/3-540-61750-7_30
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61750-1
Online ISBN: 978-3-540-70673-1
eBook Packages: Springer Book Archive