Detail publikace

A New Face Database Simultaneously Acquired in Visible, Near-Infrared and Thermal Spectrums

Originální název

A New Face Database Simultaneously Acquired in Visible, Near-Infrared and Thermal Spectrums

Anglický název

A New Face Database Simultaneously Acquired in Visible, Near-Infrared and Thermal Spectrums

Jazyk

en

Originální abstrakt

In this paper, we present a new database acquired with three different sensors (visible, near infrared and thermal) under different illumination conditions. This database consists of 41 people acquired in four different acquisition sessions, five images per session and three different illumination conditions. The total amount of pictures is 7,380 pictures. Experimental results consist of single sensor experiments as well as the combination of two and three sensors under different illumination conditions (natural, infrared and artificial illumination). We have found that the three studied spectral bands contribute in a nearly equal proportion to a combined system. Experimental results show a significant improvement combining the three spectrums, even when using a simple classifier and feature extractor. In six of the nine studied scenarios, we obtained identification rates higher or equal to 98 %, when using a trained combination rule, and two cases of nine when using a fixed rule.

Anglický abstrakt

In this paper, we present a new database acquired with three different sensors (visible, near infrared and thermal) under different illumination conditions. This database consists of 41 people acquired in four different acquisition sessions, five images per session and three different illumination conditions. The total amount of pictures is 7,380 pictures. Experimental results consist of single sensor experiments as well as the combination of two and three sensors under different illumination conditions (natural, infrared and artificial illumination). We have found that the three studied spectral bands contribute in a nearly equal proportion to a combined system. Experimental results show a significant improvement combining the three spectrums, even when using a simple classifier and feature extractor. In six of the nine studied scenarios, we obtained identification rates higher or equal to 98 %, when using a trained combination rule, and two cases of nine when using a fixed rule.

BibTex


@article{BUT94969,
  author="Virginia {Espinosa-Duró} and Marcos {Faúndez Zanuy} and Jiří {Mekyska}",
  title="A New Face Database Simultaneously Acquired in Visible, Near-Infrared and Thermal Spectrums",
  annote="In this paper, we present a new database acquired with three different sensors (visible, near infrared and thermal) under different illumination conditions. This database consists of 41 people acquired in four different acquisition sessions, five images per session and three different illumination conditions. The total amount of pictures is 7,380 pictures. Experimental results consist of single sensor experiments as well as the combination of two and three sensors under different illumination conditions (natural, infrared and artificial illumination). We have found that the three studied spectral bands contribute in a nearly equal proportion to a combined system. Experimental results show a significant improvement combining the three spectrums, even when using a simple classifier and feature extractor. In six of the nine studied scenarios, we obtained identification rates higher or equal to 98 %, when using a trained combination rule, and two cases of nine when using a fixed rule.",
  chapter="94969",
  number="1",
  volume="5",
  year="2013",
  month="march",
  pages="119--135",
  type="journal article"
}