Publication detail

Gender Recognition Using PCA and DCT of Face Images

ŠMIRG, O. FAÚNDEZ ZANUY, M. GRASSI, M. MEKYSKA, J. MIKULKA, J.

Original Title

Gender Recognition Using PCA and DCT of Face Images

English Title

Gender Recognition Using PCA and DCT of Face Images

Type

journal article

Language

en

Original Abstract

In this paper we propose a gender recognition algorithm of face images. We have used PCA and DCT for dimensionality reduction. The algorithm is based on a genetic algorithm to improve the selection of training set of images for the PCA algorithm. Genetic algorithm helps to select the images, which best represent each gender, from the image database. We have evaluated a nearest neighbor classifier as well as a neural network. Experimental results show a correct identification rate of 85,9%.

English abstract

In this paper we propose a gender recognition algorithm of face images. We have used PCA and DCT for dimensionality reduction. The algorithm is based on a genetic algorithm to improve the selection of training set of images for the PCA algorithm. Genetic algorithm helps to select the images, which best represent each gender, from the image database. We have evaluated a nearest neighbor classifier as well as a neural network. Experimental results show a correct identification rate of 85,9%.

Keywords

PCA, DCT, gender recognition, face, Genetic algorithm

RIV year

2011

Released

10.06.2011

Publisher

Springer-Verlag

Location

Berlin Heidelberg

Pages from

220

Pages to

227

Pages count

7

BibTex


@article{BUT36035,
  author="Ondřej {Šmirg} and Marcos {Faúndez Zanuy} and Marco {Grassi} and Jiří {Mekyska} and Jan {Mikulka}",
  title="Gender Recognition Using PCA and DCT of Face Images",
  annote="In this paper we propose a gender recognition algorithm of face images. We have used PCA and DCT for dimensionality reduction. The algorithm is based on a genetic algorithm to improve the selection of training set of images for the PCA algorithm. Genetic algorithm helps to select the images, which best represent each gender, from the image database. We have evaluated a nearest neighbor classifier as well as a neural network. Experimental results show a correct identification rate of 85,9%.",
  address="Springer-Verlag",
  chapter="36035",
  institution="Springer-Verlag",
  number="6",
  volume="6692",
  year="2011",
  month="june",
  pages="220--227",
  publisher="Springer-Verlag",
  type="journal article"
}