Exploring Facial Expression Effects in 3D Face Recognition Using Partial ICP

This paper investigates facial expression effects in face recognition from 3D shape using partial ICP. The partial ICP method could implicitly and dynamically extract the rigid parts of facial surface by selecting a part of nearest points pairs to calculate dissimilarity measure during registration of facial surfaces. The method is expected to be able to get much better performance than other methods in 3D face recognition under expression variation for its dynamic extraction of rigid parts of facial surface at the same time of matching. We also present an effective method for coarse alignment of facial shape, which is fully automatic. Experiments on 3D face database of 360 models with 40 subjects, 9 scans with four different kinds of expression for each subject, show partial ICP is very promising, compared with PCA baseline.