Open-set Face Recognition for Small Galleries Using Siamese Networks
This addresses the problem of access authentication in biometrics for scenarios with limited enrolled individuals, though it is incremental as it builds on existing Siamese Network approaches.
The paper tackles open-set face recognition for small galleries by proposing a Siamese Network to detect if a probe face is enrolled, rather than retrieving identity, and reports outperforming state-of-the-art methods like HFCN and HPLS on the FRGCv1 dataset.
Face recognition has been one of the most relevant and explored fields of Biometrics. In real-world applications, face recognition methods usually must deal with scenarios where not all probe individuals were seen during the training phase (open-set scenarios). Therefore, open-set face recognition is a subject of increasing interest as it deals with identifying individuals in a space where not all faces are known in advance. This is useful in several applications, such as access authentication, on which only a few individuals that have been previously enrolled in a gallery are allowed. The present work introduces a novel approach towards open-set face recognition focusing on small galleries and in enrollment detection, not identity retrieval. A Siamese Network architecture is proposed to learn a model to detect if a face probe is enrolled in the gallery based on a verification-like approach. Promising results were achieved for small galleries on experiments carried out on Pubfig83, FRGCv1 and LFW datasets. State-of-the-art methods like HFCN and HPLS were outperformed on FRGCv1. Besides, a new evaluation protocol is introduced for experiments in small galleries on LFW.