On the Quality and Diversity of Synthetic Face Data and its Relation to the Generator Training Data

In recent years, advances in deep learning techniques and large-scale identity-labeled datasets have enabled facial recognition algorithms to rapidly gain performance. However, due to privacy issues, ethical concerns, and regulations governing the processing, transmission, and storage of biometric samples, several publicly available face image datasets are being withdrawn by their creators. The reason is that these datasets are mostly crawled from the web with the possibility that not all users had properly consented to processing their biometric data. To mitigate this problem, synthetic face images from generative approaches are motivated to substitute the need for authentic face images to train and test face recognition. In this work, we investigate both the relation between synthetic face image data and the generator authentic training data and the relation between the authentic data and the synthetic data in general under two aspects, i.e. the general image quality and face image quality. The first term refers to perceived image quality and the second measures the utility of a face image for automatic face recognition algorithms. To further quantify these relations, we build the analyses under two terms denoted as the dissimilarity in quality values expressing the general difference in quality distributions and the dissimilarity in quality diversity expressing the diversity in the quality values.