ActiveWavelet Networks for Face Alignment

The active appearance model (AAM) algorithm has proved to be a successfulmethod for face alignment and synthesis. By elegantly combining both shapeand texture models, AAM allows fast and robust deformable image matching.However, the method is sensitive to partial occlusions and illuminationchanges. In such cases, the PCA-based texture model causes the reconstructionerror to be globally spread over the image. In this paper, we proposea 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 illuminationchanges.