Detail publikace

Applying Fusion in Thermal Face Recognition

Originální název

Applying Fusion in Thermal Face Recognition

Anglický název

Applying Fusion in Thermal Face Recognition

Jazyk

en

Originální abstrakt

Face recognition based on thermal images has minor importance in comparison to visible light spectrum recognition. Nevertheless, in the applications such as liveness detection or fever scan, the thermal face recognition is used as a standalone module, or as a part of a multi-modal biometric system. This paper investigates the combinations of many methods, used for thermal face recognition, and introduces some new and modified algorithms, which have not been used in this area yet. Moreover, we show that the choice of the best method is always limited to a certain database (input data). In order to address this problem, the multi-algorithmic biometric fusion based on the logistic regression is deployed.

Anglický abstrakt

Face recognition based on thermal images has minor importance in comparison to visible light spectrum recognition. Nevertheless, in the applications such as liveness detection or fever scan, the thermal face recognition is used as a standalone module, or as a part of a multi-modal biometric system. This paper investigates the combinations of many methods, used for thermal face recognition, and introduces some new and modified algorithms, which have not been used in this area yet. Moreover, we show that the choice of the best method is always limited to a certain database (input data). In order to address this problem, the multi-algorithmic biometric fusion based on the logistic regression is deployed.

BibTex


@inproceedings{BUT97016,
  author="Jan {Váňa} and Štěpán {Mráček} and Svetlana {Yanushkevich} and Martin {Drahanský}",
  title="Applying Fusion in Thermal Face Recognition",
  annote="
Face recognition based on thermal images has minor importance in comparison to
visible light spectrum recognition. Nevertheless, in the applications such as
liveness detection or fever scan, the thermal face recognition is used as
a standalone module, or as a part of a multi-modal biometric system. This paper
investigates the combinations of many methods, used for thermal face recognition,
and introduces some new and modified algorithms, which have not been used in this
area yet. Moreover, we show that the choice of the best method is always limited
to a certain database (input data). In order to address this problem, the
multi-algorithmic biometric fusion based on the logistic regression is deployed.",
  address="Fraunhofer Institute - Graphic Data Processing Institute",
  booktitle="BIOSIG 2012",
  chapter="97016",
  edition="Lecture Notes in Informatics (LNI) - Proceedings",
  howpublished="print",
  institution="Fraunhofer Institute - Graphic Data Processing Institute",
  number="8",
  year="2012",
  month="july",
  pages="233--244",
  publisher="Fraunhofer Institute - Graphic Data Processing Institute",
  type="conference paper"
}