Neural Computation
January 1993, Vol. 5, No. 1, Pages 61-74
(doi: 10.1162/neco.1993.5.1.61)
Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features
Article PDF (831.51 KB)
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).