Matching facial attributes in caricature-photograph pairs

This paper introduces a publicly available caricature-photograph database and some facial attribute based matching approach to foster research in caricature recognition. The proposed database consist of 200 caricatures and corresponding photomates. Our facial attribute based matching approach defines 32 qualitative features (i.e., gender, hair color, face shape, etc.) for identifying a subject. Then these qualitative features are used to match a caricature to a photograph. In our experiments, we use genetic algorithms and achieve 69% recognition rate at 10% false acceptance rate.