Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features
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 biological motivated feature extracting neuron. To evaluate the performance of this method we use a set of very detailed psychophysical 3D object recognition experiments.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 17, 1993
- Accession Number
- ADA264576
Entities
People
- Joshus I. Gold
- Nathan Intrator
Organizations
- Brown University