Deep periocular representation aiming video surveillance.
No Thumbnail Available
Date
2017
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Usually, in the deep learning community, it is claimed that generalized representations that yielding out- standing performance / effectiveness require a huge amount of data for learning, which directly affect biometric applications. However, recent works combining transfer learning from other domains have sur- mounted such data application constraints designing interesting and promising deep learning approaches in diverse scenarios where data is not so abundant. In this direction, a biometric system for the peri- ocular region based on deep learning approach is designed and applied on two non-cooperative ocular databases. Impressive representation discrimination is achieved with transfer learning from the facial do- main (a deep convolutional network, called VGG) and fine tuning in the specific periocular region domain. With this design, our proposal surmounts previous state-of-the-art results on NICE (mean decidability of 3.47 against 2.57) and MobBio (equal error rate of 5.42% against 8.73%) competition databases.
Description
Keywords
Deep learning, Transfer learning, VGG Periocular region, Video surveillance
Citation
MOREIRA, G. J. P. et al. Deep periocular representation aiming video surveillance. Pattern Recognition Letters, v. 114, p. 2-12, 2018. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0167865517304476>. Acesso em: 16 jun. 2018.