Face surveillance

Author

Gutta, Srinivas ; Huang, Jeffrey ; Kakkad, Vishal ; Wechsler, Harry

Author_Institution

Dept. of Comput. Sci., George Mason Univ., Fairfax, VA, USA

fYear

1998

fDate

4-7 Jan 1998

Firstpage

646

Lastpage

651

Abstract

Most of the research on face recognition addresses the MATCH problem and it assumes a closed universe where there is no need for a REJECT (`false positive´) option. The SURVEILLANCE problem is addressed indirectly, if at all, through the MATCH problem, where the size of the gallery rather than that of the probe set is very large. This paper addresses the proper surveillance problem where the size of the probe (`unknown image´) set vs. gallery (`known image´) set is 450 vs. 50 frontal images. We developed robust face ID verification (`classification´) and retrieval schemes based on hybrid classifiers and showed their feasibility using the FERET face data base. The hybrid classifier architecture consists of an ensemble of connectionist networks-Radial Basis Functions (RBF) and inductive decision trees (DT). Experimental results prove the feasibility of our approach and yield 97% accuracy using the probe and gallery sets specified above

Keywords

authorisation; face recognition; neural nets; MATCH problem; SURVEILLANCE problem; closed universe; connectionist networks; face recognition; inductive decision trees; robust face ID verification; Computer science; Face detection; Face recognition; Image quality; Image retrieval; Principal component analysis; Probes; Robustness; Security; Surveillance;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision, 1998. Sixth International Conference on

Conference_Location

Bombay

Print_ISBN

81-7319-221-9

Type

conf

DOI

10.1109/ICCV.1998.710786

Filename

710786