Share Email Print

Optical Engineering

Pattern Recognition Guidelines For Three-Dimensional Image Matching
Author(s): Ernest L. Hall; J. J. Hwang; F. A. Sadjadi
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An introduction to the computer image pattern recognition guidelines for accurately locating an object are presented in this paper. The accurate measurement of three-dimensional position requires a camera calibration process as well as the determination of corresponding image points in two images. The accuracy of the three-dimensional measurement depends upon the accuracy of the image matching solution. Since there is a variety of image matching techniques, the pattern recognition guidelines are reviewed which indicate that the optimum features are nonlinear, a posteriori probabilities of the measurements. These optimum features also maximize the trace of the between-class scatter matrix normalized by the mixture scatter matrix. However, the theoretical guidelines do not indicate how to determine simple measurement methods for the optimum features. Therefore, some experimental examples are presented which illustrate some practical solutions to the problem.

Paper Details

Date Published: 1 June 1981
PDF: 4 pages
Opt. Eng. 20(3) 203460 doi: 10.1117/12.7972741
Published in: Optical Engineering Volume 20, Issue 3
Show Author Affiliations
Ernest L. Hall, University of Tennessee (United States)
J. J. Hwang, University of Tennessee (United States)
F. A. Sadjadi, University of Tennessee (United States)

© SPIE. Terms of Use
Back to Top