Translator Disclaimer
Paper
28 May 1980 Computer Image Processing And Recognition
Author Affiliations +
Proceedings Volume 0220, Optics in Metrology and Quality Assurance; (1980) https://doi.org/10.1117/12.958573
Event: 1980 Los Angeles Technical Symposium, 1980, Los Angeles, United States
Abstract
An introduction to the computer image processing and recognition techniques applied 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 are 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 scattermatrix normalized by the mixture scattermatrix. However, the theoretical guidelines do not indicate simple measurement methods for the optimum features. Therefore, some experimental examples are presented which illustrate some practical solutions to the problem.
© (1980) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ernest L. Hall, J. J. Hwang, and F. A. Sadjadi "Computer Image Processing And Recognition", Proc. SPIE 0220, Optics in Metrology and Quality Assurance, (28 May 1980); https://doi.org/10.1117/12.958573
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top