Gender classification from NIR iris images using deep learning

Juan Tapia, Carlos Aravena

Resultado de la investigación: Chapter

11 Citas (Scopus)

Resumen

Gender classification from NIR iris image is a new topic with only a few papers published. All previous work on gender-from-iris tried to find the best feature extraction techniques to represent the information of the iris texture for gender classification using normalized, encoded or periocular images. However this is a new topic in deep-learning application with soft biometric. In this chapter, we show that learning gender-iris representations through the use of deep neural networks may increase the performance obtained on these tasks. To this end, we propose the application of deep-learning methods to separate the gender-from-iris images even when the amount of learning data is limited, using an unsupervised stage with Restricted Boltzmann Machine (RBM) and a supervised stage using a Convolutional Neural Network (CNN).

Idioma originalEnglish
Título de la publicación alojadaAdvances in Computer Vision and Pattern Recognition
EditorialSpringer London
Páginas219-239
Número de páginas21
VolumenPartF1
DOI
EstadoPublished - 2017

Serie de la publicación

NombreAdvances in Computer Vision and Pattern Recognition
VolumenPartF1
ISSN (versión impresa)2191-6586
ISSN (versión digital)2191-6594

Huella dactilar

Biometrics
Feature extraction
Textures
Neural networks
Deep learning
Deep neural networks

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Citar esto

Tapia, J., & Aravena, C. (2017). Gender classification from NIR iris images using deep learning. En Advances in Computer Vision and Pattern Recognition (Vol. PartF1, pp. 219-239). (Advances in Computer Vision and Pattern Recognition; Vol. PartF1). Springer London. https://doi.org/10.1007/978-3-319-61657-5_9
Tapia, Juan ; Aravena, Carlos. / Gender classification from NIR iris images using deep learning. Advances in Computer Vision and Pattern Recognition. Vol. PartF1 Springer London, 2017. pp. 219-239 (Advances in Computer Vision and Pattern Recognition).
@inbook{e9df54bac5f847efaa91e0a3742e35d0,
title = "Gender classification from NIR iris images using deep learning",
abstract = "Gender classification from NIR iris image is a new topic with only a few papers published. All previous work on gender-from-iris tried to find the best feature extraction techniques to represent the information of the iris texture for gender classification using normalized, encoded or periocular images. However this is a new topic in deep-learning application with soft biometric. In this chapter, we show that learning gender-iris representations through the use of deep neural networks may increase the performance obtained on these tasks. To this end, we propose the application of deep-learning methods to separate the gender-from-iris images even when the amount of learning data is limited, using an unsupervised stage with Restricted Boltzmann Machine (RBM) and a supervised stage using a Convolutional Neural Network (CNN).",
author = "Juan Tapia and Carlos Aravena",
year = "2017",
doi = "10.1007/978-3-319-61657-5_9",
language = "English",
volume = "PartF1",
series = "Advances in Computer Vision and Pattern Recognition",
publisher = "Springer London",
pages = "219--239",
booktitle = "Advances in Computer Vision and Pattern Recognition",
address = "United Kingdom",

}

Tapia, J & Aravena, C 2017, Gender classification from NIR iris images using deep learning. En Advances in Computer Vision and Pattern Recognition. vol. PartF1, Advances in Computer Vision and Pattern Recognition, vol. PartF1, Springer London, pp. 219-239. https://doi.org/10.1007/978-3-319-61657-5_9

Gender classification from NIR iris images using deep learning. / Tapia, Juan; Aravena, Carlos.

Advances in Computer Vision and Pattern Recognition. Vol. PartF1 Springer London, 2017. p. 219-239 (Advances in Computer Vision and Pattern Recognition; Vol. PartF1).

Resultado de la investigación: Chapter

TY - CHAP

T1 - Gender classification from NIR iris images using deep learning

AU - Tapia, Juan

AU - Aravena, Carlos

PY - 2017

Y1 - 2017

N2 - Gender classification from NIR iris image is a new topic with only a few papers published. All previous work on gender-from-iris tried to find the best feature extraction techniques to represent the information of the iris texture for gender classification using normalized, encoded or periocular images. However this is a new topic in deep-learning application with soft biometric. In this chapter, we show that learning gender-iris representations through the use of deep neural networks may increase the performance obtained on these tasks. To this end, we propose the application of deep-learning methods to separate the gender-from-iris images even when the amount of learning data is limited, using an unsupervised stage with Restricted Boltzmann Machine (RBM) and a supervised stage using a Convolutional Neural Network (CNN).

AB - Gender classification from NIR iris image is a new topic with only a few papers published. All previous work on gender-from-iris tried to find the best feature extraction techniques to represent the information of the iris texture for gender classification using normalized, encoded or periocular images. However this is a new topic in deep-learning application with soft biometric. In this chapter, we show that learning gender-iris representations through the use of deep neural networks may increase the performance obtained on these tasks. To this end, we propose the application of deep-learning methods to separate the gender-from-iris images even when the amount of learning data is limited, using an unsupervised stage with Restricted Boltzmann Machine (RBM) and a supervised stage using a Convolutional Neural Network (CNN).

UR - http://www.scopus.com/inward/record.url?scp=85028038896&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-61657-5_9

DO - 10.1007/978-3-319-61657-5_9

M3 - Chapter

VL - PartF1

T3 - Advances in Computer Vision and Pattern Recognition

SP - 219

EP - 239

BT - Advances in Computer Vision and Pattern Recognition

PB - Springer London

ER -

Tapia J, Aravena C. Gender classification from NIR iris images using deep learning. En Advances in Computer Vision and Pattern Recognition. Vol. PartF1. Springer London. 2017. p. 219-239. (Advances in Computer Vision and Pattern Recognition). https://doi.org/10.1007/978-3-319-61657-5_9