What else does your biometric data reveal? A survey on soft biometrics

Dantcheva, Antitza; Elia, Petros; Ross, A
IEEE Transactions on Information Forensics and Security, Vol. 11, N°3, March 2016, ISSN: 1556-6013

Recent research has explored the possibility of extracting ancillary information from primary biometric traits, viz., face, fingerprints, hand geometry and iris. This ancillary
information includes personal attributes such as gender, age, ethnicity, hair color, height, weight, etc. Such attributes are known as soft biometrics and have applications in surveillance and indexing biometric databases. These attributes can be used in a fusion framework to improve the matching accuracy of a primary biometric system (e.g., fusing face with gender information), or can be used to generate qualitative descriptions of an individual (e.g., "young Asian female with dark eyes and brown hair"). The latter is particularly useful in bridging the semantic gap between human and machine descriptions of biometric data. In this paper, we provide an overview of soft biometrics and discuss some of the techniques that have been proposed to extract them from image and video data. We also introduce a taxonomy for organizing and classifying soft biometric attributes, and enumerate the strengths and limitations of these attributes in the context of an operational biometric system. Finally, we discuss open research problems in this field. This survey is intended for researchers and practitioners in the field of biometrics.

DOI
HAL
Type:
Journal
Date:
2015-04-01
Department:
Systèmes de Communication
Eurecom Ref:
4587
Copyright:
© 2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/4587