Periocular Image

Periocular image analysis focuses on extracting biometric and diagnostic information from the region surrounding the eyes. Current research emphasizes developing deep learning models, including convolutional neural networks (CNNs) and vision transformers (ViTs), often combined, for tasks such as periorbital distance prediction, disease classification, and biometric authentication (including presentation attack detection). These advancements are driven by the need for objective, automated methods to improve the efficiency and accuracy of ophthalmic procedures and enhance security applications, particularly in scenarios where traditional facial recognition is compromised. The availability of open-source datasets and toolkits is accelerating progress in this field.