1 April 1993 Human face profile recognition by a P-Fourier descriptor
Author Affiliations +
Abstract
A method of recognizing human face profiles is proposed. Most conventional methods of recognizing human face profiles use fiducial marks, length of the line connecting the marks, angles between fiducial points, and other measures of profile outlines as the components of characteristic vectors. The P-Fourier descriptor developed by Uesaka can describe open curves fairly well, and it has many features of curves in the low-frequency range. We use the P-Fourier descriptor as a characteristic vector of a human face profile. We show that the P-Fourier coefficients in the low-frequency range are useful for human face profile recognition, that is, by using 31 P-Fourier coefficients, we obtained a correct recognition rate of 93.1 % for 130 subjects.
Tsunehiro Aibara, Kenji Ohue, Yoshiaki Oshita, "Human face profile recognition by a P-Fourier descriptor," Optical Engineering 32(4), (1 April 1993). https://doi.org/10.1117/12.61202
JOURNAL ARTICLE
3 PAGES


SHARE
RELATED CONTENT

Trigram-based algorithms for OCR result correction
Proceedings of SPIE (March 17 2017)
Query by sketch in DARWIN digital analysis to recognize...
Proceedings of SPIE (December 17 1998)
A Computerized Face Identity-Verification System (FAIS)
Proceedings of SPIE (June 01 1970)
Human face recognition by P-type Fourier descriptor
Proceedings of SPIE (November 01 1991)
Method of computer-aided measurement in a shooting range
Proceedings of SPIE (October 03 2000)

Back to Top