21 March 1989 Pattern Recognition Using A CMAC Based Learning System
Author Affiliations +
Proceedings Volume 1004, Automated Inspection and High-Speed Vision Architectures II; (1989); doi: 10.1117/12.948976
Event: 1988 Cambridge Symposium on Advances in Intelligent Robotics Systems, 1988, Boston, MA, United States
Abstract
This paper presents a new approach to image feature vector classification based on the Cerebellar Model Arithmetic Computer (CMAC) neural network proposed by Albus. This approach promises advantages both over traditional methods for feature vector classification and over other neural network based classifiers. One advantage is that the generalization properties inherent in the network allow the formation of highly nonlinear decision boundaries, and allow multiple disjoint regions of feature space to be defined in the same class. A second advantage is that the computation time required for network training and for vector classification is greatly reduced relative to other nonlinear classification techniques. Results from several classification experiments are presented, including the investigation of the effects of noise on classifier performance, and the learning of rotational classification invariance using feature vectors deliberately chosen to be highly sensitive to object rotation. Capabilities and limitations of this method of feature vector classification are discussed.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David J. Herold, W.Thomas Miller, L.Gordon Kraft, Filson H. Glanz, "Pattern Recognition Using A CMAC Based Learning System", Proc. SPIE 1004, Automated Inspection and High-Speed Vision Architectures II, (21 March 1989); doi: 10.1117/12.948976; https://doi.org/10.1117/12.948976
PROCEEDINGS
7 PAGES


SHARE
KEYWORDS
Image processing

Pattern recognition

Image filtering

Inspection

Neural networks

Computing systems

Detection and tracking algorithms

Back to Top