Robust face tracking based on region correspondence and its application for person based indexing system

In this paper, a face tracking-approach is proposed based on templats matching for applying a video indexing application. Typically, this method is simpler and faster than other methods, but the main drawback is the poor performance in the case of face scaling changes and template drifts. To overcome these problems, the information about the facial features is incorporated into a template matching process. First, the face template is represented by two projection histograms of the face region and matching methods are used to determine the candidate face region. The matching is done this way as it is faster to match two 1-dimensional projection histograms than it is to match one 2-dimensional image. Next, the facial features are extracted from the candidate face region and a dissimilarity measure, based on the proximity of the facial features, is used to verify the face region. Finally, an anthropometric model, based on geometrical relationship between facial features, is used to refine the face region. The template to determine the face region in the next frame is dynamically updated using the refined face region. Thus, the proposed method can adapt to scale any changes with less computational cost. Experimental results are provided to demonstrate the efficiency of the proposed method.