Abstract | ||
---|---|---|
We present a system for recognizing human faces from single images out of a large database with one image per person. The task is difficult because of image variation in terms of position, size, expression, and pose. The system collapses most of this variance by extracting concise face descriptions in the form of image graphs. In these, fiducial points on the face (eyes, mouth etc.) are described by sets of wavelet components (jets). Image graph extraction is based on a novel approach, the bunch graph, which is constructed from a small set of sample image graphs. Recognition is based on a straight-forward comparison of image graphs. We report recognition experiments on the FERET database and the Bochum database, including recognition across pose. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/3-540-63460-6_150 | Intelligent biometric techniques in fingerprint and face recognition |
Keywords | DocType | Volume |
image graph extraction,face recognition,sample image graph,object-adapted graph,accurate node positioning,elastic bunch graph matching,bunch graph,large database,elastic graph,image graph,single image,large rotation,data structure,data structures,image recognition,data mining,gabor wavelets,rotations,integral equations,wavelet transforms,kernel,graph theory,frequency,graph matching | Conference | 19 |
Issue | ISSN | ISBN |
7 | 0162-8828 | 0-8493-2055-0 |
Citations | PageRank | References |
1055 | 129.05 | 23 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laurenz Wiskott | 1 | 2065 | 242.36 |
Jean-marc Fellous | 2 | 1157 | 167.09 |
Norbert Krüger | 3 | 1055 | 129.05 |
Christopher von der Malsburg | 4 | 1055 | 129.05 |
FellousJean-Marc | 5 | 1055 | 129.05 |