Departamento de Informática da Universidade da Beira Interior
















Registered Users









SOCIA Lab. - Soft Computing and Image Analysis Group 

Department of Computer Science, University of Beira Interior, 6201-001 Covilhã Portugal




A Dataset of Ear Images Captured On-the-move in Uncontrolled Conditions




-      January 18th, 2011: The UBEAR web site is on-line.



For the sake of accuracy, present biometric recognition systems require that subjects stand close to the imaging camera for a period of several seconds until the data is captured. This cooperative behavior is required to capture images with enough quality for the recognition task. However, it simultaneously restricts the range of domains where biometric recognition can be applied, especially those where the subjects cooperation is not expectable (e.g., criminal/terrorist seek, missing children).


The main focus of the UBEAR database is to supply a data set of ear images captured in uncontrolled environments and under  uncosntrained protocols, so that images appear to be captured in real-world conditions, i.e., with subjects on-the-move and without requiring them any particular care about occlusions of the ears and poses. The goal is that this data sets constitutes a new resource for the development of more robust biometric recognition systems.



- The UBEAR database has over 4 430 images (and continuously growing). Below we can see examples of images of this database and of the corresponding binary ear segmentation masks.



The following examples illustrate some of the noise factors of this database.


Good Quality Image

Oclusion (earings)

Oclusion  (hair)

Strong Oclusion (hair)

Over Ilumination

Partially Captured Ear













DI-UBI Bloco VI Rua Marquês de Ávila e Bolama P- 6201-001 Covilhã PORTUGAL