Emblem Detections by Tracking Facial Features

Tracking facial features across large head rotations is a challenging research problem. Both 2D and 3D model based approaches have been proposed for feature analysis from multiple views. Accurate feature tracking enables useful video processing applications like emblem detection(an event or movement that symbolizes an idea), facial expressions recognition, morphing and synthesis. A crucial requirement is generalizability of the tracking framework across appearance variations, presence of facial hair and illumination changes. We propose a framework to detect emblems that combines active shape model with a predictive face aspect model to track features across large head movements and runs close to real time. Active Shape Model(ASM) is a deformable model for shape registration that detect facial features by combining prior shape information with the observed image data. Our view based framework represents various head poses by multiple 2D shape models and accounts for large head rotations by dynamically switching between them. Our switching variable (the current model to use) is discriminatively predicted from the SIFT descriptors computed over the bounding box of low resolution face image. We demonstrate the use of tracking framework to recognize high level events like head nodding, shaking and eye blinking.