Abstract | ||
---|---|---|
Interest in face recognition systems has increased signifi- cantly due to the emergence of significant commercial op- portunities in surveillance and security applications. In this paper we propose a novel technique to extract features from 3D face representations. In this technique, first the nose tip is automatically located on the range image, then the range data from a hexagonal region of interest around this landmark is decomposed using Barycentric wavelet kernels. The dimen- sionality of the extracted coefficients at each resolution l evel is reduced using principal component analysis (PCA). These new features are tested on 206 range images, and a high clas- sification accuracy is achieved using a small number of fea- tures. The obtained accuracy is competitive to that of other techniques in literature. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/ICIP.2007.4378912 | Image Processing, 2007. ICIP 2007. IEEE International Conference |
Keywords | Field | DocType |
face recognition,feature extraction,image representation,image resolution,principal component analysis,surveillance,wavelet transforms,3D face representations,Barycentric wavelet kernels,features extraction,principal component analysis,range images,security applications,surveillance applications,three dimensional face recognition system,wavelet decomposition,3D face recognition,Biometry,Triangular B-spline wavelets | Facial recognition system,Computer vision,Three-dimensional face recognition,Pattern recognition,Computer science,Feature extraction,Artificial intelligence,Region of interest,Image resolution,Principal component analysis,Wavelet,Wavelet transform | Conference |
Volume | ISSN | ISBN |
1 | 1522-4880 E-ISBN : 978-1-4244-1437-6 | 978-1-4244-1437-6 |
Citations | PageRank | References |
4 | 0.43 | 7 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sina Jahanbin | 1 | 37 | 2.58 |
Hyohoon Choi | 2 | 59 | 5.37 |
Alan C. Bovik | 3 | 3341 | 274.64 |
Kenneth R. Castleman | 4 | 91 | 12.80 |