Recognition of finite structures with application to moving objects identification

Authors:
Ewaryst Rafajłowicz;Jerzy Wietrzych
Affiliations:
Institute of Computer Engineering, Control and Robotics, Wrocław University of, Technology, Wrocław, Poland;Institute of Computer Engineering, Control and Robotics, Wrocław University of, Technology, Wrocław, Poland
Venue:
ICAISC'10 Proceedings of the 10th international conference on Artificial intelligence and soft computing: Part I
Year:
2010

Citing 10
Cited 0

ARIADNE: pattern-directed inference and hierarchical abstraction in protein structure recognition

Communications of the ACM
On radial basis function nets and kernel regression: statistical consistency, convergence rates, and receptive field size

Neural Networks
Markov random field models in computer vision

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Learning Logical Definitions from Relations

Machine Learning
Logical Structure Recognition of Scientific Bibliographic References

ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Multiple flexible structure alignment using partial order graphs

Bioinformatics
Pattern recognition algorithms based on space-filling curves and orthogonal expansions

IEEE Transactions on Information Theory
Constructive algorithms for structure learning in feedforward neural networks for regression problems

IEEE Transactions on Neural Networks
On the construction and training of reformulated radial basis function neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Our aim is to discuss problems of structure recognition in the Bayesian setting, treating structures as special cases of relations. We start from a general problem statement, which is solvable by dynamic programming for linear structures. Then, we consider splitting the problem of structure recognition into a series of pairwise relations testing, which is applicable when on-line processing of intensive data streams is necessary. An appropriate neural network structure is also proposed and tested on a video stream.