Detail publikace

Face segmentation: a comparison between visible and thermal images

Originální název

Face segmentation: a comparison between visible and thermal images

Anglický název

Face segmentation: a comparison between visible and thermal images

Jazyk

en

Originální abstrakt

Face segmentation is a first step for face biometric systems. In this paper we present a face segmentation algorithm for thermographic images. This algorithm is compared with the classic Viola and Jones algorithm used for visible images. Experimental results reveal that, when segmenting a multispectral (visible and thermal) face database, the proposed algorithm is more than 10 times faster, while the accuracy of face segmentation in thermal images is higher than in case of Viola-Jones.

Anglický abstrakt

Face segmentation is a first step for face biometric systems. In this paper we present a face segmentation algorithm for thermographic images. This algorithm is compared with the classic Viola and Jones algorithm used for visible images. Experimental results reveal that, when segmenting a multispectral (visible and thermal) face database, the proposed algorithm is more than 10 times faster, while the accuracy of face segmentation in thermal images is higher than in case of Viola-Jones.

BibTex


@proceedings{BUT66018,
  author="Jiří {Mekyska} and Virginia {Espinosa-Duró} and Marcos {Faúndez Zanuy}",
  title="Face segmentation: a comparison between visible and thermal images",
  annote="Face segmentation is a first step for face biometric systems. In this paper we present a face segmentation algorithm for thermographic images. This algorithm is compared with the classic Viola and Jones algorithm used for visible images. Experimental results reveal that, when segmenting a multispectral (visible and thermal) face database, the proposed algorithm is more than 10 times faster, while the accuracy of face segmentation in thermal images is higher than in case of Viola-Jones.",
  address="IEEE",
  chapter="66018",
  institution="IEEE",
  year="2010",
  month="october",
  pages="185--189",
  publisher="IEEE",
  type="conference proceedings"
}