Age-invariant face recognition based on identity-age shared features

Decoupling the mixed face features to obtain identity features that are not disturbed by age information is the key to achieving cross-age face recognition. Established mainstream identity feature extraction methods decouple facial representations into two components: age-related features and identity-related features, ignoring the fact that some identity-age shared features (ISF) exist, resulting in incomplete extracted identity features and limiting the further improvement of cross-age identity recognition accuracy. We redefine the component of facial representations and propose to introduce identity-age shared features to complement identity features. Specifically, the mixed face features are decoupled into pure age features, pure identity features, and identity-age shared features. The pure identity features and identity-age shared features are coupled to obtain the complete identity features. In addition, a two-stage constraint algorithm is developed to reduce the interference of age-related information on identity recognition and to enhance the independence between identity and age features. Experimental results on benchmark datasets for face aging (FG-NET, AGE-DB30, CALFW and CACD-VS) show that the proposed ISF outperforms state-of-the-art AIFR approaches, including DAL and MTLFace.