Local vs global: intelligent local face recognition

Face recognition in real world applications is a very difficult task because of image misalignments, pose and illumination variations, or occlusions. Many researchers in this field investigated both face representation and classification techniques able to deal with these drawbacks. However none of them is free from limitations. Early proposed algorithms was generally holistic, in the sense they consider the face object as a whole. Recently, challenging benchmark demonstrated they are not adequate to be applied in unconstrained environment, despite of their good performances in more controlled conditions. The researchers’ attention is now turning on local features that demonstrated to be more robust to a large set of non-monotonic distortions. Nevertheless, local operators partially overcomes some of these drawbacks, while still opening new questions on which are the criteria to select the most representative features. This is the reason why, among all the others, hybrid approaches are showing a high potential in terms of recognition accuracy when applied in uncontrolled settings, as they integrate complementary information from both local and global features