Three-dimensional object recognition using an unsupervised BCM network: the usefulness of distinguishing features

Authors:
Nathan Intrator;Joshua I. Gold
Affiliations:
-;-
Venue:
Neural Computation
Year:
1993

Citing 0
Cited 2

Recognition without Correspondence using MultidimensionalReceptive Field Histograms

International Journal of Computer Vision
Combining exploratory projection pursuit and projection pursuit regression with application to neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an object recognition scheme based on a method forfeature extraction from gray level images that corresponds torecent statistical theory, called projection pursuit, and isderived from a biologically motivated feature extracting neuron. Toevaluate the performance of this method we use a set of verydetailed psychophysical three-dimensional object recognitionexperiments (Bülthoff and Edelman 1992).