Person-Specific Face Tracking With Online Recognition

Person-specific face tracking is a challenging task for the trackers which only focus on the appearance of the target face, because distraction always happens and the identity is difficult to maintain. In this paper, we design a framework combining an off-line detector, an on-line tracker and an on-line recognizer to complete the tracking of person-specific face. Recognizer is the key component in our framework, because the most confident target face will be selected by the recognizer from the pool of detected and tracked faces. Since there is no much prior information about the identities available and the face poses change frequently in surveillance scenarios, accurate recognition is extremely difficult and an on-line formulation is required. In order to ensure the precision of identity recognition with different poses, we project the extracted features of faces to a latent space with the help of Canonical Correlation Analysis (CCA) technique, and then these projected features are incrementally trained using an on-line SVM (LASVM). Experimental results demonstrate that our person-specific face tracking outperforms several state-of-the-art face trackers.