Two-tiered face verification with low-memory footprint for mobile devices

Hybrid Image Generation

Abstract

Mobile devices had 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 a more secure and effortless authentication. In this work, we propose a facial verification method optimized 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 photo corresponds to the device owner. To train a CNN for the verification task, we propose a hybrid-image input, which allows the network to process encoded information of a pair of face images. Our experiments show that the proposed solution outperforms state-of-the-art face verification methods, providing a 4x speedup when processing an image in recent smartphone models. Additionally, we show that the two-tiered procedure can be coupled with existing face verification CNNs improving their accuracy and efficiency. We also present a new dataset of selfie pictures – RCD dataset – that hopefully will support future research in this scenario.

Publication
IET Biometrics

BibTeX

@article{padilha2020two,
  title={Two-tiered face verification with low-memory footprint for mobile devices},
  author={Padilha, Rafael and Andal{\'o}, Fernanda and Bertocco, Gabriel and Almeida, Waldir and Dias, William and Resek, Thiago and Torres, Ricardo and Wainer, Jacques and Rocha, Anderson},
  journal={IET Biometrics},
  volume={9},
  issue={5},
  pages={205–215},
  year={2020},
  publisher={IET}
}