Facial Similarity across Age,disguise, illumination and pose (TP-P2)

Author(s) : Narayanan Ramanathan (Electrical & Computer Engineering, USA) Amit Chowdhury (University of California, Riverside, USA) Rama Chellappa (Centre for Automation Research, USA)

Abstract : Illumination, pose variations, disguises, aging effects and expression variations are some of the key factors that affect the performance of face recognition systems. In this paper, our emphasis is on deriving a measure of similarity between faces. The similarity measure provides insights into how the above mentioned variations may affect the performance of face recognition systems. In the process of computing the similarity measure between faces, we compensate for pose variations using the notion of `Half-faces' and circumvent the problem of non-uniform illumination. We use the similarity measure to retrieve similar faces from a database containing multiple images of individuals.

Menu