4EyesFace--Detecting, Tracking and Aligning Faces in Real-TimeChangbo Hu, Rogerio Feris, Matthew Turk |
| |||||||||||||||||
OverviewThe goal of the 4EyesFace is to find faces from video, then track the face pose and align the face to models. DetailsWe use Adaboost face detector to detect faces and provide the initial face position for tracking. For different poses we have three view models. To align the faces to the models, we proposed a method called Active Wavelet Networks (AWN). AWN is an improvement over Active Appearance Models (by Tim Cootes). 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. The following images show this case.
AWN replaces the AAM texture model by a wavelet network representation. The face representation based on wavelet networks has variable precision according to the number of wavelets. 
The view-based shape models in our experiments are showed below.
Since we consider spatially localized wavelets for modeling texture, our method shows more robustness against partial occlusions and some illumination changes. We refer to our publications for performance graphs and more figures. 
PublicationsChangbo Hu, Rogerio Feris and Matthew Turk. Changbo Hu, Rogerio Feris and Matthew Turk. More InformationRelated Projects
| ||||||||||||||||||
