6 April 1995 Feature space trajectory neural net classifier
Author Affiliations +
Abstract
A new classifier neural network is described for distortion-invariant multi-class pattern recognition. The input analog neurons are a feature space. All distorted aspect views of one object are described by a trajectory in feature space. Classification of test data involves calculation of the closest feature space trajectory. Pose estimation is achieved by determining the closest line segment on the closest trajectory. Rejection of false class clutter is demonstrated. Comparisons are made to other neural network classifiers, including a radial basis function and a new standard backpropagation neural net. The shapes of the different decision surfaces produced by our feature space trajectory classifier are analyzed.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Leonard Neiberg, Leonard Neiberg, David P. Casasent, David P. Casasent, } "Feature space trajectory neural net classifier", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); doi: 10.1117/12.205141; https://doi.org/10.1117/12.205141
PROCEEDINGS
12 PAGES


SHARE
Back to Top