Abstract | ||
---|---|---|
In this paper, we propose the application of masks as a means to mitigate expression-distortions on 3D faces and to enhance their recognition performance. Masking becomes necessary to de-emphasize the face regions that deform un- der expression. We have conducted experiments with various masks, namely, ellipse-shaped binary masks, Gaussian, su- per-Gaussian and raised-cosine masks. The design issues of the masks, such as the mask size, the centre, the support region, the decay rate of the tails, etc. are studied and ad- justed with respect to their recognition performances. We show first that warping the depth values of corresponding face points onto the same spatial coordinates while obtain- ing the 2D depth images is beneficial, and second, that proper masking can add several percentage points to the recognition performance. |
Year | Venue | Keywords |
---|---|---|
2007 | EUSIPCO | emotion recognition,face recognition,image matching,iterative methods,3d face region-based recognition,gaussian mask,ellipse-shaped binary mask,expression variations,expression-distortion mitigation,iterative closest point algorithm,masking,raised-cosine mask,recognition performance enhancement,spatial coordinates,super-gaussian mask,tail decay rate |
Field | DocType | ISBN |
Facial recognition system,Computer vision,Image warping,Pattern recognition,Spatial reference system,Masking (art),Gaussian,Solid modeling,Artificial intelligence,Mathematics,Principal component analysis,Binary number | Conference | 978-839-2134-04-6 |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Helin Dutaacõ | 1 | 0 | 0.34 |
Berk Gokberk | 2 | 113 | 6.23 |
Bülent Sankur | 3 | 1128 | 73.91 |
lale akarun | 4 | 1201 | 70.68 |