Integrating Recognition Paradigms in a Multiple-Path Architecture

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.

[1]  Dorin Comaniciu,et al.  Robust analysis of feature spaces: color image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Jasjit S. Suri,et al.  White Matter/Gray Matter Boundary Segmentation Using Geometric Snakes: A Fuzzy Deformable Model , 2001, ICAPR.

[3]  Lutz Priese,et al.  A Fast Hybrid Color Segmentation Method , 1993, DAGM-Symposium.

[4]  Edwin R. Hancock,et al.  Analysis of Curved Textured Surfaces Using Local Spectral Distortion , 2001, ICAPR.

[5]  J. Flusser,et al.  Combined invariants to convolution and rotation , 2000, IWISPA 2000. Proceedings of the First International Workshop on Image and Signal Processing and Analysis. in conjunction with 22nd International Conference on Information Technology Interfaces. (IEEE.

[6]  Jan Wolter,et al.  A structure-oriented approach to assembly sequence planning , 1997, IEEE Trans. Robotics Autom..

[7]  Helge J. Ritter,et al.  A multi-directional multiple-path recognition scheme for complex objects applied to the domain of a wooden toy kit , 1999, Pattern Recognit. Lett..

[8]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[9]  Roberto Marcondes Cesar Junior,et al.  Locating and Tracking Facial Landmarks Using Gabor Wavelet Networks , 2001, ICAPR.

[10]  Yunsick Sung,et al.  Author index , 1994, Regulatory Peptides.

[11]  Helge J. Ritter,et al.  A Hybrid Object Recognition Architecture , 1996, ICANN.

[12]  Sameer Singh,et al.  Texture Analysis Experiments with Meastex and Vistex Benchmarks , 2001, ICAPR.

[13]  Terry Caelli,et al.  Complex Images and Complex Filters: A Unified Model for Encoding and Matching Shape and Colour , 2001, ICAPR.

[14]  Daniel Schlüter,et al.  Perceptual Grouping using Markov Random Fields and Cue Integration of Contour and Region Information , 1998 .

[15]  Stefan Posch,et al.  Mask-Oriented Grouping Operations in a Contour-Based Approach , 1995 .

[16]  Franz Kummert,et al.  Integration of regions and contours for object recognition , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[17]  Daniel Schlüter,et al.  Using Markov random fields for contour-based grouping , 1997, Proceedings of International Conference on Image Processing.

[18]  B. Parhami.  Voting algorithms , 1994 .

[19]  Franz Kummert,et al.  Towards and Image Understanding Architecture for a Situated Artificial Communicator , 1999 .

[20]  Franz Kummert,et al.  Modeling and recognition of assembled objects , 1998, IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200).