Facial Profile Biometrics: Domain Adaptation and Deep Learning Approaches

Previous studies indicate that human facial profiles are considered as a biometric modality and there is a bilateral symmetry in facial profile biometrics. This study examines the bilateral symmetry of the human face profiles and presents the analysis of facial profile images for recognition. A method from few-shot learning framework is proposed here to extract facial profile features. Based on domain adaptation and reverse validation, we introduce a technique known as reverse learning (RL) in this paper for the same side profiles to achieve a recognition rate of 85%. In addition, to investigate bilateral symmetry, our reverse learning model is trained and validated on the left side face profiles to measure the cross recognition of 71% for right side face profiles. Also in this paper, we assume that the right face profiles are unlabelled, and we therefore apply our reverse learning method to include the right face profiles in the validation stage to improve the performance of our algorithm for opposite side recognition. Our numerical experiments indicate an accuracy of 84.5% for cross recognition which, to the best of our knowledge, demonstrates higher performance than the state-of-the-art methods for datasets with similar number of subjects. Our algorithm based on few-shot learning can achieve high accuracies for a dataset characterized with as low as four samples per group.