Abstract
In this paper, we study a bootstrapped learning procedure applied to corner detection using synthetic training data generated from a grey-level model of a corner feature which permits sampling of the pattern space at arbitrary density as well as providing a self-consistent validation set to assess the classifier generalisation. Since adequate learning of the whole mapping by a single neural network is problematic we partition data across modules using bootstrapping and which we then combine by a meta-learning stage. We test the hierarchical classifier on real images and compare results with those obtained by a monolithic network.
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Hinton, G.E.: Connectionist Learning Procedures. Artificial Intelligence 40 (1989) 185–234
Auda, G, Kamel, M.: Modular Neural Networks— a Survey. Int. J. Neural Systems 9 (1999) 129–151.
Kumar, R., Rockett, P.I.: Multiobjective Genetic Algorithm Partitioning for Hierarchical Learning of High-Dimensional Pattern Spaces: A Learning-follows-Decomposition Strategy. IEEE Trans. Neural Networks 9 (1998) 822–830
Chen, W.C., Thacker, N.A., Rockett, P.I.: A Neural Network for Probabilistic Edge Labelling with a Step Edge Model. IEE Proc.— Vision, Image & Signal 143 (1986) 41–50
Chen, W.C.: Probabilistic Labelling of Edge and Corner Image Features with Neural Networks. Ph.D. Thesis. Dept. Electronic & Electrical Engineering, Sheffield Univ., 1996.
Richard, M.D., Lippmann, R.P.: Neural Network Classifiers Estimates Bayesian a posteriori probabilities. Neural Computation 3 (1991) 461–483
Lacey, A.J., Thacker, N.A., Seed, N.L.: Smart Feature Detector Using an Invariance Network Architecture. Proc. 6th British Machine Vision Conf. (1995) 327–336
Jacobs, J.A.: Methods for Combining Experts’ Probability Assessments. Neural Computations 7 (1995) 867–888
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kumar, R., Rockett, P. (2002). A Bootstrapped Modular Learning Approach for Scaling and Generalisation of Grey-Level Corner Detection. In: Pal, N.R., Sugeno, M. (eds) Advances in Soft Computing — AFSS 2002. AFSS 2002. Lecture Notes in Computer Science(), vol 2275. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45631-7_53
Download citation
DOI: https://doi.org/10.1007/3-540-45631-7_53
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43150-3
Online ISBN: 978-3-540-45631-5
eBook Packages: Springer Book Archive