New AI model identifies people by eyes alone—with 98% accuracy
Researchers trained neural networks on nearly 2 million eye-region images to develop periocular recognition—a biometric authentication method that works from photos of just the area around the eyes. The advance could reshape identity verification for banking, border security, and mobile devices, especially in low-light or masked scenarios where full-face recognition fails.
Originaltitel: Leveraging Large-Scale Face Datasets for Deep Periocular Recognition via Ocular Cropping
<p>We focus on ocular biometrics, specifically the periocular region (the area around the eye), which offers high discrimination and minimal acquisition constraints. We evaluate three Convolutional Neural Network architectures of varying depth and complexity to assess their effectiveness for periocular recognition. The networks are trained on 1,907,572 ocular crops extracted from the large-scale VGGFace2 database. This significantly contrasts with existing works, which typically rely on small-scale periocular datasets for training having only a few thousand images. Experiments are conducted with ocular images from VGGFace2-Pose, a subset of VGGFace2 containing in-the-wild face images, and the UFPR-Periocular database, which consists of selfies captured via mobile devices with user guidance on the screen. Due to the uncontrolled conditions of VGGFace2, the Equal Error Rates (EERs) obtained with ocular crops range from 9–15%, noticeably higher than the 3–6% EERs achieved using full-face images. In contrast, UFPR-Periocular yields significantly better performance (EERs of 1–2%), thanks to higher image quality and more consistent acquisition protocols. To the best of our knowledge, these are the lowest reported EERs on the UFPR dataset to date.</p><p>© 2026 The Author(s), under exclusive license to Springer Nature Switzerland AG</p>