Gender recognition on real world faces based on shape representation and neural network

Olasimbo Ayodeji Arigbabu, Sharifah Mumtazah Syed Ahmad, Wan Azizun Wan Adnan, Salman Yussof, Vahab Iranmanesh, Fahad Layth Malallah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Gender as a soft biometric attribute has been extensively investigated in the domain of computer vision because of its numerous potential application areas. However, studies have shown that gender recognition performance can be hindered by improper alignment of facial images. As a result, previous experiments have adopted face alignment as an important stage in the recognition process, before performing feature extraction. In this paper, the problem of recognizing human gender from unaligned real world faces using single image per individual is investigated. The use of feature descriptor to form shape representation of face images with any arbitrary orientation from the cropped version of Labeled Faces in the Wild (LFW) dataset is proposed. By combining the feature extraction technique with artificial neural network for classification, a recognition rate of 89.3% is attained.

Original languageEnglish
Title of host publication2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479943913
DOIs
Publication statusPublished - 30 Jul 2014
Event2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - Kuala Lumpur, Malaysia
Duration: 03 Jun 201405 Jun 2014

Publication series

Name2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings

Other

Other2014 International Conference on Computer and Information Sciences, ICCOINS 2014
CountryMalaysia
CityKuala Lumpur
Period03/06/1405/06/14

Fingerprint

Feature extraction
Neural networks
Biometrics
Computer vision
Experiments

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Environmental Engineering
  • Renewable Energy, Sustainability and the Environment
  • Computer Science Applications

Cite this

Arigbabu, O. A., Ahmad, S. M. S., Adnan, W. A. W., Yussof, S., Iranmanesh, V., & Malallah, F. L. (2014). Gender recognition on real world faces based on shape representation and neural network. In 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings [6868361] (2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCOINS.2014.6868361
Arigbabu, Olasimbo Ayodeji ; Ahmad, Sharifah Mumtazah Syed ; Adnan, Wan Azizun Wan ; Yussof, Salman ; Iranmanesh, Vahab ; Malallah, Fahad Layth. / Gender recognition on real world faces based on shape representation and neural network. 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. (2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings).
@inproceedings{ec4b9ff84abb4cbd866c31655e8e3d94,
title = "Gender recognition on real world faces based on shape representation and neural network",
abstract = "Gender as a soft biometric attribute has been extensively investigated in the domain of computer vision because of its numerous potential application areas. However, studies have shown that gender recognition performance can be hindered by improper alignment of facial images. As a result, previous experiments have adopted face alignment as an important stage in the recognition process, before performing feature extraction. In this paper, the problem of recognizing human gender from unaligned real world faces using single image per individual is investigated. The use of feature descriptor to form shape representation of face images with any arbitrary orientation from the cropped version of Labeled Faces in the Wild (LFW) dataset is proposed. By combining the feature extraction technique with artificial neural network for classification, a recognition rate of 89.3{\%} is attained.",
author = "Arigbabu, {Olasimbo Ayodeji} and Ahmad, {Sharifah Mumtazah Syed} and Adnan, {Wan Azizun Wan} and Salman Yussof and Vahab Iranmanesh and Malallah, {Fahad Layth}",
year = "2014",
month = "7",
day = "30",
doi = "10.1109/ICCOINS.2014.6868361",
language = "English",
series = "2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings",
address = "United States",

}

Arigbabu, OA, Ahmad, SMS, Adnan, WAW, Yussof, S, Iranmanesh, V & Malallah, FL 2014, Gender recognition on real world faces based on shape representation and neural network. in 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings., 6868361, 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2014 International Conference on Computer and Information Sciences, ICCOINS 2014, Kuala Lumpur, Malaysia, 03/06/14. https://doi.org/10.1109/ICCOINS.2014.6868361

Gender recognition on real world faces based on shape representation and neural network. / Arigbabu, Olasimbo Ayodeji; Ahmad, Sharifah Mumtazah Syed; Adnan, Wan Azizun Wan; Yussof, Salman; Iranmanesh, Vahab; Malallah, Fahad Layth.

2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. 6868361 (2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Gender recognition on real world faces based on shape representation and neural network

AU - Arigbabu, Olasimbo Ayodeji

AU - Ahmad, Sharifah Mumtazah Syed

AU - Adnan, Wan Azizun Wan

AU - Yussof, Salman

AU - Iranmanesh, Vahab

AU - Malallah, Fahad Layth

PY - 2014/7/30

Y1 - 2014/7/30

N2 - Gender as a soft biometric attribute has been extensively investigated in the domain of computer vision because of its numerous potential application areas. However, studies have shown that gender recognition performance can be hindered by improper alignment of facial images. As a result, previous experiments have adopted face alignment as an important stage in the recognition process, before performing feature extraction. In this paper, the problem of recognizing human gender from unaligned real world faces using single image per individual is investigated. The use of feature descriptor to form shape representation of face images with any arbitrary orientation from the cropped version of Labeled Faces in the Wild (LFW) dataset is proposed. By combining the feature extraction technique with artificial neural network for classification, a recognition rate of 89.3% is attained.

AB - Gender as a soft biometric attribute has been extensively investigated in the domain of computer vision because of its numerous potential application areas. However, studies have shown that gender recognition performance can be hindered by improper alignment of facial images. As a result, previous experiments have adopted face alignment as an important stage in the recognition process, before performing feature extraction. In this paper, the problem of recognizing human gender from unaligned real world faces using single image per individual is investigated. The use of feature descriptor to form shape representation of face images with any arbitrary orientation from the cropped version of Labeled Faces in the Wild (LFW) dataset is proposed. By combining the feature extraction technique with artificial neural network for classification, a recognition rate of 89.3% is attained.

UR - http://www.scopus.com/inward/record.url?scp=84938768065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938768065&partnerID=8YFLogxK

U2 - 10.1109/ICCOINS.2014.6868361

DO - 10.1109/ICCOINS.2014.6868361

M3 - Conference contribution

T3 - 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings

BT - 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Arigbabu OA, Ahmad SMS, Adnan WAW, Yussof S, Iranmanesh V, Malallah FL. Gender recognition on real world faces based on shape representation and neural network. In 2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. 6868361. (2014 International Conference on Computer and Information Sciences, ICCOINS 2014 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2014 - Proceedings). https://doi.org/10.1109/ICCOINS.2014.6868361