Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features
- 1 January 1993
- journal article
- Published by MIT Press in Neural Computation
- Vol. 5 (1) , 61-74
- https://doi.org/10.1162/neco.1993.5.1.61
Abstract
We propose an object recognition scheme based on a method for feature extraction from gray level images that corresponds to recent statistical theory, called projection pursuit, and is derived from a biologically motivated feature extracting neuron. To evaluate the performance of this method we use a set of very detailed psychophysical three-dimensional object recognition experiments (Bülthoff and Edelman 1992).Keywords
This publication has 12 references indexed in Scilit:
- Psychophysical support for a two-dimensional view interpolation theory of object recognition.Proceedings of the National Academy of Sciences, 1992
- Objective function formulation of the BCM theory of visual cortical plasticity: Statistical connections, stability conditionsNeural Networks, 1992
- Feature Extraction Using an Unsupervised Neural NetworkNeural Computation, 1992
- A self-organizing multiple-view representation of 3D objectsBiological Cybernetics, 1991
- A network that learns to recognize three-dimensional objectsNature, 1990
- Fast Learning in Networks of Locally-Tuned Processing UnitsNeural Computation, 1989
- A Physiological Basis for a Theory of Synapse ModificationScience, 1987
- Exploratory Projection PursuitJournal of the American Statistical Association, 1987
- Projection PursuitThe Annals of Statistics, 1985
- THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMSAnnals of Eugenics, 1936