Abstract
Four decades of intensive research in computer vision have lead to numerous computational paradigms. This fact is comprehensible since problems like object recognition or scene descriptions are of high complexity, have different aspects and can be attacked by processing various features. In this paper we propose an architecture that combines the advantages of different paradigms in pattern recognition. Voting and Bayesian networks provide a computational framework to integrate approaches to knowledge based and probabilistic reasoning as well as neural computations.
This work has been supported by the German Research Foundation within SFB 360.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D.H. Ballard and C.M. Brown. Computer Vision. Prentice Hall, 1982.
C. Bauckhage, G.A. Fink, G. Heidemann, N. Jungclaus, F. Kummert, S. Posch, H. Ritter, G. Sagerer, and D. Schliiter. Towards an image understanding architec ture for a situated artificial communicator. Int. J. of Pattern Recognition and Image Analysis, 9(4):542-, 1999.
C. Bauckhage, F. Kummert, and G. Sagerer. Modeling and recognition of assembled objects. In Proc. IEEE Conf. IECON 98, pages 2051–2056, 1998.
E. Braun, G. Heidemann, H. Ritter, and G. Sagerer. A multi-directional multiple path recognition scheme for complex objects applied to the domain of a wooden toy kit. Pattern Recognition Letters, 20:1085–1091, 1999.
S. Chakrabarty and J. Wolter. A Structure-Oriented Approach to Assembly Sequence Planning. IEEE Trans, on Robotics and Automation, 13(l):14–29, 1997.
D. Comaniciu and P. Meer. Robust analysis of feature space: Color image segmenta tion. In Proc. IEEE Conf. CVPR, pages 750–755, 1997.
G. Heidemann. Ein flexibel einsetzbares Objekterkennungssystem auf der Basis neuronaler Netze. PhD thesis, Universitat Bielefeld, 1998.
G. Heidemann, F. Kummert, H. Ritter, and G. Sagerer. A hybrid object recognition architecture. In Proc. ICANN 96, pages 305–310, 1996.
A. Leonardis. Image Analysis Using Parametric Models. PhD thesis, University of Ljubljana, 1993.
A. Mafimann and S. Posch. Mask-oriented grouping operations in a contour-based approach. In Proc. IEEE 2nd Asian Conf. on Computer Vision, volume III, pages 58–61, 1995.
A. Mafimann, S. Posch, G. Sagerer, and D. Schliiter. Using markov random fields for contour-based grouping. In Proc. IEEE Int. Conf. on Image Processing, volume II, pages 207–210, 1997.
B. Parhami. Voting algorithm. IEEE Trans, on Reliability, 43(4):617–629, 1994.
S. Posch and D. Schliiter. Perceptual grouping using markov random fields and cue integration of contour and region information. TR 98/10, SFB 360, Univ. of Bielefeld, 1998.
L. Priese and V. Rehrmann. A fast hybrid color segmentation method. In S. Poppel and H. Handels, editors, Mustererkennung 93, pages 297–304, 1993.
D. Reisfeld, H. Wolfson, and Y. Yeshurun. Context-free attentional operators: The generalized symmetry transform. Int. J. of Computer Vision, 14:119–130, 1995.
D. Schliiter, F. Kummert, G. Sagerer, and S. Posch. Integration of regions and con tours for object recognition. In Proc. 15th Int. Conf. on Pattern Recognition, volume I, pages 944–947, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sagerer, G. et al. (2001). Integrating Recognition Paradigms in a Multiple-path Architecture. In: Singh, S., Murshed, N., Kropatsch, W. (eds) Advances in Pattern Recognition — ICAPR 2001. ICAPR 2001. Lecture Notes in Computer Science, vol 2013. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44732-6_21
Download citation
DOI: https://doi.org/10.1007/3-540-44732-6_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41767-5
Online ISBN: 978-3-540-44732-0
eBook Packages: Springer Book Archive