Name
Abstract | ||
|---|---|---|
In this paper, a methodology for facial feature identification and localization approach is proposed based on binary neural network algorithms. We present a head pose and facial expression invariant 3D shape descriptor called mesh-like multi circle curvature descriptor (MMCCD), which provides more 3D curvature attributes than other similar approaches. To search and match the feature patterns with more attributes, we use advanced uncertain reasoning architecture (AURA) k-nearest neighbour algorithms to encode, train and match the feature patterns based on 3D shape curvature. Experiments performed on the FRGC dataset (4950 3D faces) with pose and expression variations show that our approach is able to achieve an accurate (over 99.69% nose tip identification) and robust identification and localization of facial features. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/IJCNN.2009.5178700 | IJCNN |
Keywords | Field | DocType |
image representation,image matching,face recognition,advanced uncertain reasoning architecture,shape curvature,mesh-like multicircle curvature descriptor,feature pattern,k-nearest neighbour algorithm,robust identification,aura,facial feature localization,pose estimation,localization approach,facial expression invariant,feature extraction,head pose descriptor,expression variation,curvature attribute,binary neural network,nose tip identification,3d facial feature localization approach,mmccd,facial feature identification,binary neural network algorithm,facial feature,frgc dataset,feature pattern matching,neural nets,pattern matching,neural networks,crops,facial expression,benchmark testing,face,neural network,shape,robustness,face detection | Computer science,Pose,Robustness (computer science),Artificial intelligence,Face detection,Artificial neural network,Computer vision,Facial recognition system,Curvature,Pattern recognition,Feature extraction,Facial expression,Machine learning | Conference |
ISSN | ISBN | Citations |
1098-7576 E-ISBN : 978-1-4244-3553-1 | 978-1-4244-3553-1 | 3 |
PageRank | References | Authors |
0.51 | 13 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Quan Ju | 1 | 30 | 2.83 |
| Simon O'keefe | 2 | 41 | 11.71 |
| Jim Austin | 3 | 1167 | 66.82 |