Open AccessTwo‐tiered face verification with low‐memory footprint for mobile devices
Author(s) -
Padilha Rafael,
Andaló Fernanda A.,
Bertocco Gabriel,
Almeida Waldir R.,
Dias William,
Resek Thiago,
Torres Ricardo da S.,
Wainer Jacques,
Rocha Anderson
Publication year - 2020
Publication title -
iet biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 28
ISSN - 2047-4946
DOI - 10.1049/iet-bmt.2020.0031
Subject(s) - computer science , convolutional neural network , mobile device , biometrics , footprint , artificial intelligence , face (sociological concept) , task (project management) , set (abstract data type) , speedup , memory footprint , facial recognition system , authentication (law) , computer vision , human–computer interaction , machine learning , data mining , pattern recognition (psychology) , computer security , world wide web , paleontology , social science , management , sociology , economics , biology , programming language , operating system
Mobile devices have their popularity and affordability greatly increased in recent years. As a consequence of their ubiquity, these devices now carry all sorts of personal data that should be accessed only by their owner. Even though knowledge‐based procedures are still the main methods to secure the owner's identity, recently biometric traits have been employed for more secure and effortless authentication. In this work, the authors propose a facial verification method optimised to the mobile environment. It consists of a two‐tiered procedure that combines hand‐crafted features and a convolutional neural network (CNN) to verify if the person depicted in a photograph corresponds to the device owner. To train a CNN for the verification task, the authors propose a hybrid‐image input, which allows the network to process encoded information of a pair of face images. The proposed experiments show that the solution outperforms state of the art face verification methods, providing a 4× speedup when processing an image in recent smartphone models. Additionally, the authors show that the two‐tiered procedure can be coupled with existing face verification CNNs improving their accuracy and efficiency. They also present a new data set of selfie pictures – RECOD Selfie data set – that hopefully will support future research in this scenario.