Departamento de Informaica da Universidade da Beira Interior


 

 

 

 

 

 

 

 

 

 

 

 

 

Home

UBEAR

Registered Users

About

 

 

 

 

 

 

Contact:

SOCIA Lab.: Soft Computing and Image Analysis Group 

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

hugomcp@di.ubi.pt

http://www2.clustrmaps.com/stats/maps-no_clusters/ubear.di.ubi.pt-thumb.jpg

 

 

UBEAR

 

 

In order to broad the applicability of biometric systems, the data acquisition constraints required for reliable recognition are receiving increasing attention. For some of the traits (e.g., face and iris) significant research efforts were already made toward the development of systems able to operate in completely unconstrained conditions. For other traits (e.g., the ear) no similar efforts are known. The main purpose of the UBEAR data set is to supply to the research community a new data set of ear images, which main distinguishing feature is that its images were acquired from on-the-move subjects, under varying lighting conditions and without demanding to subjects any particular care regarding ear occlusions and poses. The data set is freely available to the research community and should constitute a valuable tool in assessing the possibility of performing reliable ear biometric recognition in such challenging conditions.

 

Video Acquisition Framework and Set-Up

Camera

Stingray F-504B 2/3”

Focal length

35 mm

Color Representation

gray scale

Video Resolution

1280x960 pixels

Frames per second

15

Video Codec

Avi uncompressed

Details of the selected frames

Image Resolution

1280x960 pixels

Color Representation

gray scale

Image Codec

tiff

Volunteers

Totals = Subjects 126; Ears 252; Images 4 430

Gender = Male: 44.62%; Female: 55.38%

Age = [0,20]: 43.85% [21,25]: 47.69%

[26,30]: 3.85% [31,35]: 2.31% [36,99]: 2.30%

 

The setup of the video and imaging framework is given in the above table. The video capture sequence starts with all subjects facing front and 3 meters apart from the camera sideways, it’s also required of the individual to move his head upwards, downwards, outwards, towards. After these, subjects should step ahead and backwards from the initial position. For each subject both ears were captured in two different sessions, giving a total of four videos per subject. Each video sequence was manually analyzed and 17 frames were selected according to the following criteria:

-      5 frames when the subject was stepping ahead and backwards,

-      3 frames of the subject’s head moving upwards,

-      3 frames of the subject’s head moving downwards,

-      3 frames of the subject’s head moving outwards,

-      3 frames of the subject’s head moving towards.

 

Download Application Form: [pdf]

 

All requests for the UBEAR database must be directed (by email) to the following address: hugomcp@di.ubi.pt. Applicants should manually fill, sign, scan and attach the application form to the given email address. Upon receipt of an executed copy of the signed application form, access instructions will be given.

 

Download


Password Protected ZIP Files version 1.0: [zip1] [zip2][zip3] [zip4]
Password Protected ZIP Files version 1.1: [zip1] [zip2][zip3] [zip4] [readme]

 

Citation:

 

All documents and papers that report on research that uses the UBEAR database must database by including an appropriate citation:

 

Rui Raposo, Edmundo Hoyle, Adolfo Peixinho, and Hugo Proença. UBEAR: A dataset of ear images captured on-the-move in uncontrolled conditions, in 2011 IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (SSCI 2011 CIBIM), Paris, France, April 11 - April 15, pag. 84-90, 2011.


 

 

Publications to SOCIA Lab.:

 

A copy of all reports and papers that use the UBEAR database and are for public or general release must be forwarded immediately upon release or publication to the SOCIA Lab. email address: socia@di.ubi.pt

 

 

 

 

 

 

 

 

 











 


 

 

fghfghfghfgh 


DI-UBI Bloco VI Rua Marques de Avila e Bolama P- 6201-001 Covilha, PORTUGAL