Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
From few to many: Illumination cone models for face recognition under variable lighting and pose
Autore:
Georghiades, AS; Belhumeur, PN; Kriegman, DJ;
Indirizzi:
Yale Univ, Dept Elect Engn, New Haven, CT 06520 USA Yale Univ New Haven CT USA 06520 Dept Elect Engn, New Haven, CT 06520 USA Yale Univ, Dept Comp Sci, New Haven, CT 06520 USA Yale Univ New Haven CT USA 06520 , Dept Comp Sci, New Haven, CT 06520 USA Univ Illinois, Dept Comp Sci, Urbana, IL 61801 USA Univ Illinois Urbana IL USA 61801 is, Dept Comp Sci, Urbana, IL 61801 USA Univ Illinois, Beckman Inst, Urbana, IL 61801 USA Univ Illinois Urbana ILUSA 61801 ois, Beckman Inst, Urbana, IL 61801 USA
Titolo Testata:
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
fascicolo: 6, volume: 23, anno: 2001,
pagine: 643 - 660
SICI:
0162-8828(200106)23:6<643:FFTMIC>2.0.ZU;2-W
Fonte:
ISI
Lingua:
ENG
Soggetto:
NEURAL-NETWORK; IMAGE; OBJECT; MOTION; IDENTIFICATION; INFORMATION; EIGENFACES; ALGORITHMS; SHAPE;
Keywords:
face recognition; image-based rendering; appearance-based vision; face modeling; illumination and pose modeling; lighting; illumination cones; generative models;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
77
Recensione:
Indirizzi per estratti:
Indirizzo: Georghiades, AS Yale Univ, Dept Elect Engn, 51 Prospect St,POB 208285, NewHaven, CT 06520USA Yale Univ 51 Prospect St,POB 208285 New Haven CT USA 06520
Citazione:
A.S. Georghiades et al., "From few to many: Illumination cone models for face recognition under variable lighting and pose", IEEE PATT A, 23(6), 2001, pp. 643-660

Abstract

We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an object in fixed pose, but under all possible illumination conditions, is a convex cone in the space of images. Using a small number of training images of each face taken with different lighting directions, the shape and albedo of the face can be reconstructed. In turn, this reconstruction serves as a generative model that can be used to render-or synthesize-images of the face under novel poses and illumination conditions. The pose space is then sampled and, for each pose. the corresponding illumination cone is approximated by a low-dimensional linear subspace whose basis vectors are estimated using the generative model. Our recognition algorithm assigns to a test image the identity of the closest approximated illumination cone (based on Euclidean distance within the image space). We test our face recognition method on 4,050 images from the Yale Face Database B; these images contain 405 viewing conditions (9 poses x 45 illumination conditions) for 10 individuals. The method performs almost without error, except on the most extreme lighting directions, and significantly outperforms popular recognition methods that do not use a generative model.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/01/20 alle ore 06:32:21