Abstract
In this paper, we present a new 3D face recognition approach. Full automation is provided through the use of advanced multi-stage alignment algorithms, resilience to facial expressions by employing a deformable model framework, and invariance to 3D capture devices through suitable preprocessing steps. In addition, scalability in both time and space is achieved by converting 3D facial scans into compact wavelet metadata. We present results on the largest known, and now publicly-available, Face Recognition Grand Challenge 3D facial database consisting of several thousand scans. To the best of our knowledge, our approach has achieved the highest accuracy on this dataset.
Original language | English (US) |
---|---|
Pages | 869-878 |
Number of pages | 10 |
State | Published - 2006 |
Event | 2006 17th British Machine Vision Conference, BMVC 2006 - Edinburgh, United Kingdom Duration: Sep 4 2006 → Sep 7 2006 |
Conference
Conference | 2006 17th British Machine Vision Conference, BMVC 2006 |
---|---|
Country/Territory | United Kingdom |
City | Edinburgh |
Period | 9/4/06 → 9/7/06 |
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition