Selfie Periocular Verification using an Efficient Super-Resolution Approach

TL;DR

This paper introduces an efficient super-resolution method for improving selfie periocular verification, significantly reducing model size while maintaining high recognition accuracy across various face recognition systems.

Contribution

It proposes a lightweight super-resolution algorithm optimized for periocular biometrics, balancing efficiency and quality, with a novel loss function based on image sharpness.

Findings

Reduces model parameters from over 2 million to under 30,000.

Achieves verification EER below 9% with FaceNet without image resizing.

Maintains high recognition performance with resized images up to 4x.

Abstract

Selfie-based biometrics has great potential for a wide range of applications since, e.g. periocular verification is contactless and is safe to use in pandemics such as COVID-19, when a major portion of a face is covered by a facial mask. Despite its advantages, selfie-based biometrics presents challenges since there is limited control over data acquisition at different distances. Therefore, Super-Resolution (SR) has to be used to increase the quality of the eye images and to keep or improve the recognition performance. We propose an Efficient Single Image Super-Resolution algorithm, which takes into account a trade-off between the efficiency and the size of its filters. To that end, the method implements a loss function based on the Sharpness metric used to evaluate iris images quality. Our method drastically reduces the number of parameters compared to the state-of-the-art: from 2,170,142 to 28,654. Our best results on remote verification systems with no redimensioning reached an EER of 8.89\% for FaceNet, 12.14% for VGGFace, and 12.81% for ArcFace. Then, embedding vectors were extracted from SR images, the FaceNet-based system yielded an EER of 8.92% for a resizing of x2, 8.85% for x3, and 9.32% for x4.