MUBIDUS-I: A multibiometric and multipurpose dataset

Abstract

Individual biometric traits can seldom fulfill the requirements of security systems in the wild, so researchers were led to investigate multi-biometric/multi-modal systems. This has produced increasing demand for datasets suitable for validating multi-trait and multi-modal biometric systems. Recent devices available for image acquisition and processing can provide a wide range of data sources for biometric applications. The purpose of this work is to present a new multi-biometric dataset that includes a number of traits and acquisition devices wider than most existing datasets. It includes images and videos acquired from 80 subjects in an indoor and outdoor environment, in controlled and non-controlled conditions. Traits such as face, periocular regions, ear, iris, and others are acquired by cameras, mobile devices, and a drone. The data are structured to support experiments adhering to the most common protocols in the literature.