DocumentCode :
318329
Title :
Fitting implicit quartics for use in feature extraction
Author :
Redding, Nicholas J. ; Whatmough, Robert C.
Author_Institution :
Defence Sci. & Technol. Organ., Salisbury, SA, Australia
Volume :
2
fYear :
1997
fDate :
26-29 Oct 1997
Firstpage :
410
Abstract :
This paper presents a method for extracting features from images using implicit quartics in two variables. These features have been particularly designed to be appropriate for the image understanding problem involving oblique ionograms, but they are more generally applicable. Attention is given to the problem of choosing a suitable fitting metric, and the paper presents a robust procedure (exact orthogonal distance regression) for achieving a good fit
Keywords :
curve fitting; feature extraction; ionospheric techniques; least squares approximations; polynomials; exact orthogonal distance regression; feature extraction; fitting metric; image understanding; implicit quartics; nonlinear least squares; oblique ionograms; polynomial curves; robust procedure; variables; Australia; Data preprocessing; Feature extraction; Frequency measurement; Ionosphere; Particle measurements; Pixel; Polynomials; Robustness; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
Type :
conf
DOI :
10.1109/ICIP.1997.638794
Filename :
638794
Link To Document :
بازگشت