On the ethnic classification of Pakistani face using deep learning

Shelina Khalid Jilani; Hassan Ugail; Ali Maina Bukar; Andrew Logan

doi:10.1109/CW.2019.00039

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

Vision Sciences

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

5 Citations (Scopus)

1083 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 language	English
Title of host publication	2019 International Conference on Cyberworlds (CW)
Publisher	IEEE
Pages	191-198
Number of pages	8
ISBN (Electronic)	9781728122977
ISBN (Print)	9781728122984
DOIs	https://doi.org/10.1109/CW.2019.00039
Publication status	Published - Oct 2019
Event	2019 International Conference on Cyberworlds - Kyoto, Japan Duration: 2 Oct 2019 → 4 Oct 2019 https://ieeexplore.ieee.org/xpl/conhome/8910333/proceeding

Publication series

Name	International Conference on Cyberworlds (CW)
ISSN (Print)	2642-357X
ISSN (Electronic)	2642-3596

Conference

Conference	2019 International Conference on Cyberworlds
Abbreviated title	CW 2019
Country/Territory	Japan
City	Kyoto
Period	2/10/19 → 4/10/19
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8910333/proceeding

Keywords

ethnicity
Pakistani
deep learning
residual network
classification

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Hardware and Architecture
Computer Science Applications
Media Technology
Computational Theory and Mathematics
Computer Graphics and Computer-Aided Design

Documents and Links

10.1109/CW.2019.00039

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.
Author accepted manuscript, 955 KB

Cite this

@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; 2019 International Conference on Cyberworlds, CW 2019 ; Conference date: 02-10-2019 Through 04-10-2019",

year = "2019",

month = oct,

doi = "10.1109/CW.2019.00039",

language = "English",

isbn = "9781728122984",

series = "International Conference on Cyberworlds (CW)",

publisher = "IEEE",

pages = "191--198",

booktitle = "2019 International Conference on Cyberworlds (CW)",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/8910333/proceeding",

}

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 - 2019/10

Y1 - 2019/10

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

T3 - International Conference on Cyberworlds (CW)

SP - 191

EP - 198

BT - 2019 International Conference on Cyberworlds (CW)

PB - IEEE

T2 - 2019 International Conference on Cyberworlds

Y2 - 2 October 2019 through 4 October 2019

ER -

On the ethnic classification of Pakistani face using deep learning

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Documents and Links

Fingerprint

Cite this