Face recognition: Eigenface, elastic matching, and neural nets
- Univ. of Wisconsin, Milwaukee, WI (United States). Dept. of Electrical Engineering and Computer Science
- Intelligent Medical Imaging Inc., Palm Beach Gardens, FL (United States)
- Lawrence Livermore National Lab., CA (United States). Inst. for Scientific Computing Research
This paper is a comparative study of three recently proposed algorithms for face recognition: eigenface, autoassociation and classification neural nets, and elastic matching. After these algorithms were analyzed under a common statistical decision framework, they were evaluated experimentally on four individual data bases, each with a moderate subject size, and a combined data base with more than a hundred different subjects. Analysis and experimental results indicate that the eigenface algorithm, which is essentially a minimum distance classifier, works well when lighting variation is small. Its performance deteriorates significantly as lighting variation increases. The elastic matching algorithm, on the other hand, is insensitive to lighting, face position, and expression variations and therefore is more versatile. The performance of the autoassociation and classification nets is upper bounded by that of the eigenface but is more difficult to implement in practice.
- Sponsoring Organization:
- National Science Foundation, Washington, DC (United States); USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 563916
- Journal Information:
- Proceedings of the IEEE, Vol. 85, Issue 9; Other Information: PBD: Sep 1997
- Country of Publication:
- United States
- Language:
- English
Similar Records
FaceID: A face detection and recognition system
Illumination-invariant face recognition with a contrast sensitive silicon retina