Heterogeneous Face Recognition

Face recognition is one of the most important applications in computer vision. This is because face recognition could achieve efficient and convenient identity verification in uncontrolled scenarios. With the development of deep learning models in image processing, superior recognition accuracy has been achieved recently [6, 59]. However, real face images are captured through different sources, such as sketch artists and infrared imaging devices, called heterogeneous faces. Furthermore, matching face images in different modalities, which is referred to as heterogeneous face recognition (HFR), is now attracting growing attention in both biometrics research and industry.