Face recognition by local and global analysis

Faces are highly deformable objects which may easily change their appearance over time. Not all face areas are subject to the same variability and they do not have the same relevance for recognition. Therefore, selecting and decoupling the information from independent areas of the face is of paramount importance to improve the robustness of any face recognition technique. In forensic applications it is rather important to identify an individual by peculiar, subjective features, which uniquely characterize his/her face. This paper discusses how to select relevant local features on the face and use these features to uniquely identify a subject. For identification purposes, both a global and local (as recognition from parts) matching strategy is proposed. The local strategy is based on matching individual salient facial SIFT features as connected to selected facial landmarks. As for the global matching strategy, relevant SIFT features are combined together to form a single feature.