Open-set Face Recognition for Small Galleries Using Siamese Networks

Abstract

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 (openset 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-ofthe-art methods like HFCN and HPLS were outperformed on FRGCv1. Besides, a new evaluation protocol is introduced for experiments in small galleries on LFW.

Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition

“…[19]. In this domain, apart from EVT based methods, solutions based on siamese networks have been proposed to address the open-set as they are metric learning methods, and their similarity scores can be thresholded to perform recognition [45]. Although they do not fit the data stream context, they could be used as a baseline for comparison purposes [48].…”

Object Recognition Using Mechanical Impact, Viscoelasticity, and Surface Friction During Interaction

“…Previous works show that OSR has been successfully applied in various fields such as object detection [7]- [9], face recognition [10]- [12], and antonymous driving [13]. However, these systems are not able to incrementally learn new information from novel objects and label them.…”

Sistema De Busca Reversa De Imagens Utilizando Aprendizado Por Contraste

“…Assim como em busca reversa de imagens, sistemas de reconhecimento facial recebem uma imagem de um rosto humano e buscam rostos similares em uma base. Uma abordagem que tem sido utilizada com sucesso para reconhecimento facial é o treinamento de redes siamesas por aprendizado por contraste (Wu et al, 2017), (Salomon et al, 2020).…”