Pattern Recognition Guidelines For Three-Dimensional Image Matching

Ernest L. Hall; J. J. Hwang; F. A. Sadjadi

doi:10.1117/12.7972741

1 June 1981 Pattern Recognition Guidelines For Three-Dimensional Image Matching

Ernest L. Hall, J. J. Hwang, F. A. Sadjadi

Author Affiliations +

Optical Engineering, Vol. 20, Issue 3, 203460 (June 1981). https://doi.org/10.1117/12.7972741

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.

Citation Download Citation

Ernest L. Hall, J. J. Hwang, and F. A. Sadjadi "Pattern Recognition Guidelines For Three-Dimensional Image Matching," Optical Engineering 20(3), 203460 (1 June 1981). https://doi.org/10.1117/12.7972741

Published: 1 June 1981

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available