Abstract
We study the problem of how to detect “interesting objects” appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis. Since the basis (a library of image templates) is over-redundant, there are infinitely many ways to decompose I. To select the “best” decomposition we first propose a global optimization procedure that considers a concave cost function derived from a “weighted L p norm” with 0<p<-1. This concave cost function selects as few coefficients as possible producing a sparse representation of the image and handle occlusions. However, it contains multiple local minima. We identify all local minima so that a global optimization is possible by visiting all of them. Secondly, because the number of local minima grows exponentially with the number of templates, we investigate a greedy “L p Matching Pursuit” strategy.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
J. Ben-Arie and K. R. Rao, “On the Recognition of Occluded Shapes and Generic Faces Using Multiple-Template Expansion Matching”, Proceedings IEEE International Conference on Pattern Recognition, New York City, 1993.
F. Bergeaud and S. Mallat, “Matching Pursuit of Images”, SPIE, Orlando, 1995.
S. Chen and D. Donoho, “Atomic Decomposition by Basis Pursuit”, Technical Report, Stanford University, May, 1995.
S. Chen and D. Donoho, “Basis Pursuit”, TR, Stanford University, Nov. 1994.
R. Coifman and V. Wickerhauser, “Entropy-based Algorithms for Best Basis Selection”, IEEE Transactions on Information Theory, vol. 38, no. 2, 1992.
T. H. Cormen, C. E. Leiserson and R. L. Rivest, Introduction to Algorithms, McGraw-Hill, 1990.
M. J. Donahue and D. Geiger, “Template Matching and Function Decomposition Using Non-Minimal Spanning Sets”, Technical Report, Siemens, 1993.
H. Ekblom, “L p -methods for Robust Regression”, BIT 14, p.22–32, 1973.
D. Field, “What Is the Goal of Sensory Coding”, Neural Comp. 6, p.559–601, 1994.
J. H. Friedman and W. Stuetzle, “Projection Pursuit Regression”, Journal of the American Statistical Association, vol. 76, p.817–823, 1981.
P. J. Huber, “Projection Pursuit”, The Ann. of Stat., vol. 13, No.2, p.435–475, 1985.
P. J. Huber, Robust Statistics, John Wiley & Sons, New York, 1981.
T. Liu, M. Donahue, D. Geiger and R. Hummel, “Sparse Representations for Image Decomposition”, Technical Report, CS, Courant Institute, NYU, 1996.
S. Mallat and Z. Zhang, “Matching Pursuit with Time-Frequency Dictionaries”, IEEE Trans. on Signal Processing, Dec. 1993.
P. J. Rousseeuw and A. Leroy, Robust Regression and Outlier Detection, John Wiley, New York, 1987.
M. Turk and A. Pentland, “Eigenfaces for Recognition”, J. of Cognitive Neuroscience, vol. 3, p.71–86, 1991.
B. Uhrin, “An Elementary Constructive Approach to Discrete Linear l p -approximation, 0<p<-+∞”, Colloquia Mathematica Societatis János Bolyai, 58. Approximation Theory, Kecskemét, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, TL., Donahue, M., Geiger, D., Hummel, R. (1996). Image recognition with occlusions. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015566
Download citation
DOI: https://doi.org/10.1007/BFb0015566
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive