DMCA
M (2003) Active wavelet networks for face alignment
Cached
Download Links
| Venue: | In: Proceedings of British machine vision conference |
| Citations: | 19 - 3 self |
BibTeX
@INPROCEEDINGS{Hu_m(2003),
author = {Changbo Hu and Rogerio Feris and Matthew Turk},
title = {M (2003) Active wavelet networks for face alignment},
booktitle = {In: Proceedings of British machine vision conference},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The active appearance model (AAM) algorithm has proved to be a successful method for face alignment and synthesis. By elegantly combining both shape and texture models, AAM allows fast and robust deformable image matching. However, the method is sensitive to partial occlusions and illumination changes. In such cases, the PCA-based texture model causes the reconstruction error to be globally spread over the image. In this paper, we propose a new method for face alignment called active wavelet networks (AWN), which replaces the AAM texture model by a wavelet network representation. Since we consider spatially localized wavelets for modeling texture, our method shows more robustness against partial occlusions and some illumination changes. 1
