Kinship verification from facial images by scalable similarity fusion

Kinship verification using face images (KVFI) is a relatively new and challenging problem in computer vision and biometrics, while kin relationship in psychology has been well studied over the past decades. Recent advances in KVFI have shown that learning an effective similarity metric plays a critical role in the verification problem. However, most existing distance metric learning (DML) based KVFI methods use batch learning techniques to seek an optimal kin similarity metric, making them less scalable in practical verification tasks. To address this, we propose in this paper a scalable similarity learning (SSL) method for KVFI. Unlike existing DML-based solutions, SSL aims to learn a diagonal bilinear similarity model by online truncated gradient learning, which enjoys superiority in scalability and computational efficiency for practical KVFI with high-dimensional data. We further derive a multiview SSL algorithm by optimal fusion of the diagonal similarity models from multiple feature representations in a coherent online process, such that the interactions and correlations in multiview kin data can be leveraged to obtain refined and high-level information. Empirically, we evaluate our proposed method on two benchmark datasets against the state-of-the-art DML-based solutions, and the results demonstrate that our method can achieve competitive or better verification performance, and enjoys the superiority in scalability and computational efficiency.