Share Email Print

Proceedings Paper

SIFT based iris feature extraction and matching
Author(s): Juan Geng; Yan Li; Tao Chian
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Iris feature extraction is the crucial stage of the whole iris recognition process. A brief introduction of iris recognition system is made firstly in this paper, then presented the method of iris feature extraction and matching using Scale Invariant Feature Transform (SIFT). Through analyzing iris feature extraction and matching method, we found in conventional iris recognition system, Iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured iris image data, are impacted of natural illumination or other variant conditions easily. So this paper used SIFT feature which is invariant to image scaling and rotation, and partially invariant to change in illumination. They are also well localized in both the spatial and frequency domains. SIFT feature shows a higher feasibility in the iris feature extraction and matching process.

Paper Details

Date Published: 25 July 2007
PDF: 10 pages
Proc. SPIE 6753, Geoinformatics 2007: Geospatial Information Science, 67532F (25 July 2007); doi: 10.1117/12.761945
Show Author Affiliations
Juan Geng, Nanjing Univ. (China)
Yan Li, Nanjing Univ. (China)
Tao Chian, Nanjing Univ. (China)

Published in SPIE Proceedings Vol. 6753:
Geoinformatics 2007: Geospatial Information Science
Jingming Chen; Yingxia Pu, Editor(s)

© SPIE. Terms of Use
Back to Top