Abstract
We address the problem of describing, recognizing, and learning generic, free-form objects in real-world scenes. We introduce a hybrid appearance-based approach, IDEAL, where objects are encoded as a loose collections of parts and the relations between them. The key features of this new approach are the structural part decomposition combining multi-scale wavelet segmentation and hierarchical blobs, and learning to recognize generic object categories, exhibiting large intra-class variability, from real examples with automatic model acquisition.
This research was partially supported by the Austrian Science Foundation (FWF) research program Theory and Applications of Digital Image Processing and Pattern Recognition grant S7002 Robust and Adaptive Methods for Image Understanding.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
R. Bergevin and M.D. Levine. Generic object recognition: building and matching coarse descriptions from line drawings. IEEE Trans. Pattern Analysis and Machine Intelligence, 1(15):19–36, 1993.
I. Biedermann. Recognition-by-components: A theory of human image understanding. Psychological Review, 94(2):115–147, 1987.
W. Bischof and T. Caelli. Learning structural descriptions: a new technique for conditional clustering and rule generation. Pattern Recognition, pages 689–697, May 1994.
R.A. Brooks. Symbolic reasoning among 3-d models and 2-d images. Artificial Intelligence, 17:285–348, 1981.
M. Burge, W. Burger, and W. Mayr. Learning to recognize generic visual categories using a hybrid structural approach. In ICIP-96, volume 2, pages 321–324, Lausanne, Switzerland, September 16–19 1996. IEEE Press. Online at http://www.cast.uni-linz.ac.at/Vision/papers/icip-96/
M. Burge, W. Burger, and W. Mayr. Recognition and learning with polymorphic structural components. In 13th ICPR, volume 1, pages 19–23, Vienna, Austria, August 25–30 1996. IEEE Press. Online at http://www.cast.unilinz.ac.at/Vision/papers/icpr-96/
W. Burger and B. Bhanu. Signal-to-symbol conversion for structural object recognition using hidden Markov models. In Proc. ARPA Image Understanding Workshop, pages 1287–1291, Monterey, CA, Nov. 1994.
L. Cinque, D. Yasuda, L.G. Shapiro, S. Tanimoto, and B. Allen. An improved algorithm for relational distance graph matching. PR, 29(2):349–359, February 1996.
S. Edelman. On learning to recognize 3-d objects from examples. PAMI, 15(8):833–837, August 1993.
K.-S. Fu. Syntactic Pattern recognition and Applications. Englewood Cliffs, 1992.
A.K. Jain and R. Hoffman. Evidence-based recognition of 3D objects. PAMI, 10(6):783–802, November 1988.
T. Lindeberg. Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention. IJCV, 11(3):283–318, 1993.
David G. Lowe. Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31:355–395, 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Burge, M., Burger, W. (1997). Learning visual ideals. In: Pichler, F., Moreno-Díaz, R. (eds) Computer Aided Systems Theory — EUROCAST'97. EUROCAST 1997. Lecture Notes in Computer Science, vol 1333. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0025067
Download citation
DOI: https://doi.org/10.1007/BFb0025067
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63811-7
Online ISBN: 978-3-540-69651-3
eBook Packages: Springer Book Archive