High-Quality Facial Keypoints Matching with Motion Smoothness Constraint and 3D Model Constraint
Xianxian Zeng, Xiaodong Wang, Kairui Chen, Peichu Ye, Xiaorui Hu, Dong Li, Yun Zhang · 2018
Pore-scale facial features, similar to fingerprints and irises, are effective to distinguish human identities. Nonetheless, there is a few of pore-scale facial feature database, which constrains deep learning methods to be employed of generating pore-scale facial features. In this paper, we propose a novel method by merging motion smoothness constraint and 3D model constraint, to generate a large and complex pore-scale facial feature database. The proposed method uses a powerful motion smoothness constraint in feature matching, rather than the standard ratio-test, and utilizes 3D model constraint to eliminate the incorrect matching. In the experiment, by using the proposed method, the matched numbers into high matched quality are two times higher than state-of-the-art with the same local features.