On the ethnic classification of Pakistani face using deep learning

Shelina Khalid Jilani*, Hassan Ugail, Ali Maina Bukar, Andrew Logan

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Downloads (Pure)

Abstract

Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.
Original languageEnglish
Title of host publication2019 International Conference on Cyberworlds (CW)
PublisherIEEE
Pages191-198
Number of pages8
ISBN (Electronic)9781728122977
ISBN (Print)9781728122984
DOIs
Publication statusPublished - 5 Dec 2019

Publication series

Name
ISSN (Print)2642-357X
ISSN (Electronic)2642-3596

Fingerprint

Learning algorithms
Learning systems
Support vector machines
Deep learning
Feature extraction
Identification (control systems)
Experiments

Keywords

  • ethnicity
  • Pakistani
  • deep learning
  • residual network
  • classification

Cite this

Jilani, S. K., Ugail, H., Bukar, A. M., & Logan, A. (2019). On the ethnic classification of Pakistani face using deep learning. In 2019 International Conference on Cyberworlds (CW) (pp. 191-198). IEEE. https://doi.org/10.1109/CW.2019.00039
Jilani, Shelina Khalid ; Ugail, Hassan ; Bukar, Ali Maina ; Logan, Andrew. / On the ethnic classification of Pakistani face using deep learning. 2019 International Conference on Cyberworlds (CW). IEEE, 2019. pp. 191-198
@inproceedings{8e29334bd5c2478d94c75ebe8920f260,
title = "On the ethnic classification of Pakistani face using deep learning",
abstract = "Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2{\%} for full-face ethnicity classification, followed closely by 91.7{\%} and 95.7{\%} for the nose and mouth respectively.",
keywords = "ethnicity, Pakistani, deep learning, residual network, classification",
author = "Jilani, {Shelina Khalid} and Hassan Ugail and Bukar, {Ali Maina} and Andrew Logan",
note = "Acceptance in SAN AAM: no embargo",
year = "2019",
month = "12",
day = "5",
doi = "10.1109/CW.2019.00039",
language = "English",
isbn = "9781728122984",
publisher = "IEEE",
pages = "191--198",
booktitle = "2019 International Conference on Cyberworlds (CW)",

}

Jilani, SK, Ugail, H, Bukar, AM & Logan, A 2019, On the ethnic classification of Pakistani face using deep learning. in 2019 International Conference on Cyberworlds (CW). IEEE, pp. 191-198. https://doi.org/10.1109/CW.2019.00039

On the ethnic classification of Pakistani face using deep learning. / Jilani, Shelina Khalid; Ugail, Hassan; Bukar, Ali Maina; Logan, Andrew.

2019 International Conference on Cyberworlds (CW). IEEE, 2019. p. 191-198.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - On the ethnic classification of Pakistani face using deep learning

AU - Jilani, Shelina Khalid

AU - Ugail, Hassan

AU - Bukar, Ali Maina

AU - Logan, Andrew

N1 - Acceptance in SAN AAM: no embargo

PY - 2019/12/5

Y1 - 2019/12/5

N2 - Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.

AB - Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.

KW - ethnicity

KW - Pakistani

KW - deep learning

KW - residual network

KW - classification

U2 - 10.1109/CW.2019.00039

DO - 10.1109/CW.2019.00039

M3 - Conference contribution

SN - 9781728122984

SP - 191

EP - 198

BT - 2019 International Conference on Cyberworlds (CW)

PB - IEEE

ER -

Jilani SK, Ugail H, Bukar AM, Logan A. On the ethnic classification of Pakistani face using deep learning. In 2019 International Conference on Cyberworlds (CW). IEEE. 2019. p. 191-198 https://doi.org/10.1109/CW.2019.00039

Documents and Links

  • Jilani, S. et al (2019) On the ethnic classification of Pakistani face using deep learning

    Copyright © 2019 IEEE. This is a post-peer review, pre-copy edited version of the article and may differ slightly from the final published version of the work. This work is made available in line with the publisher policy. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

    Accepted author manuscript, 955 KB