A machine learning approach for ethnic classification: the British Pakistani face

Shelina Khalid Jilani, Hassan Ugail, Ali M. Bukar, Andrew Logan, Tasnim Munshi

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

23 Downloads (Pure)

Abstract

Ethnicity is one of the most salient clues to face identity. Analysis of ethnicity-specific facial data is a challenging problem and predominantly carried out using computer-based algorithms. Current published literature focusses on the use of frontal face images. We addressed the challenge of binary (British Pakistani or other ethnicity) ethnicity classification using profile facial images. The proposed framework is based on the extraction of geometric features using 10 anthropometric facial landmarks, within a purpose-built, novel database of 135 multi-ethnic and multi-racial subjects and a total of 675 face images. Image dimensionality was reduced using Principle Component Analysis and Partial Least Square Regression. Classification was performed using Linear Support Vector Machine. The results of this framework are promising with 71.11% ethnic classification accuracy using a PCA algorithm + SVM as a classifier, and 76.03% using PLS algorithm + SVM as a classifier.
Original languageEnglish
Title of host publication2017 International Conference on Cyberworlds (CW)
PublisherIEEE
Pages170-173
Number of pages4
ISBN (Electronic)9781538620892
DOIs
Publication statusPublished - 1 Dec 2017

Fingerprint

Learning systems
Classifiers
Support vector machines

Keywords

  • machine learning
  • face identity
  • ethnic classification

Cite this

Jilani, S. K., Ugail, H., Bukar, A. M., Logan, A., & Munshi, T. (2017). A machine learning approach for ethnic classification: the British Pakistani face. In 2017 International Conference on Cyberworlds (CW) (pp. 170-173). IEEE. https://doi.org/10.1109/CW.2017.27
Jilani, Shelina Khalid ; Ugail, Hassan ; Bukar, Ali M. ; Logan, Andrew ; Munshi, Tasnim. / A machine learning approach for ethnic classification: the British Pakistani face. 2017 International Conference on Cyberworlds (CW). IEEE, 2017. pp. 170-173
@inproceedings{0140f2148ae347a8a381af517ae6408a,
title = "A machine learning approach for ethnic classification: the British Pakistani face",
abstract = "Ethnicity is one of the most salient clues to face identity. Analysis of ethnicity-specific facial data is a challenging problem and predominantly carried out using computer-based algorithms. Current published literature focusses on the use of frontal face images. We addressed the challenge of binary (British Pakistani or other ethnicity) ethnicity classification using profile facial images. The proposed framework is based on the extraction of geometric features using 10 anthropometric facial landmarks, within a purpose-built, novel database of 135 multi-ethnic and multi-racial subjects and a total of 675 face images. Image dimensionality was reduced using Principle Component Analysis and Partial Least Square Regression. Classification was performed using Linear Support Vector Machine. The results of this framework are promising with 71.11{\%} ethnic classification accuracy using a PCA algorithm + SVM as a classifier, and 76.03{\%} using PLS algorithm + SVM as a classifier.",
keywords = "machine learning, face identity, ethnic classification",
author = "Jilani, {Shelina Khalid} and Hassan Ugail and Bukar, {Ali M.} and Andrew Logan and Tasnim Munshi",
note = "Acceptance and AAM requested (note this was published when GCU author at different HEI; AAM not in other rep) ET 22/2/19 Acceptance in SAN No ISSN found for output, out of policy scope. ST 13/11/19",
year = "2017",
month = "12",
day = "1",
doi = "10.1109/CW.2017.27",
language = "English",
pages = "170--173",
booktitle = "2017 International Conference on Cyberworlds (CW)",
publisher = "IEEE",

}

Jilani, SK, Ugail, H, Bukar, AM, Logan, A & Munshi, T 2017, A machine learning approach for ethnic classification: the British Pakistani face. in 2017 International Conference on Cyberworlds (CW). IEEE, pp. 170-173. https://doi.org/10.1109/CW.2017.27

A machine learning approach for ethnic classification: the British Pakistani face. / Jilani, Shelina Khalid; Ugail, Hassan; Bukar, Ali M.; Logan, Andrew; Munshi, Tasnim.

2017 International Conference on Cyberworlds (CW). IEEE, 2017. p. 170-173.

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

TY - GEN

T1 - A machine learning approach for ethnic classification: the British Pakistani face

AU - Jilani, Shelina Khalid

AU - Ugail, Hassan

AU - Bukar, Ali M.

AU - Logan, Andrew

AU - Munshi, Tasnim

N1 - Acceptance and AAM requested (note this was published when GCU author at different HEI; AAM not in other rep) ET 22/2/19 Acceptance in SAN No ISSN found for output, out of policy scope. ST 13/11/19

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Ethnicity is one of the most salient clues to face identity. Analysis of ethnicity-specific facial data is a challenging problem and predominantly carried out using computer-based algorithms. Current published literature focusses on the use of frontal face images. We addressed the challenge of binary (British Pakistani or other ethnicity) ethnicity classification using profile facial images. The proposed framework is based on the extraction of geometric features using 10 anthropometric facial landmarks, within a purpose-built, novel database of 135 multi-ethnic and multi-racial subjects and a total of 675 face images. Image dimensionality was reduced using Principle Component Analysis and Partial Least Square Regression. Classification was performed using Linear Support Vector Machine. The results of this framework are promising with 71.11% ethnic classification accuracy using a PCA algorithm + SVM as a classifier, and 76.03% using PLS algorithm + SVM as a classifier.

AB - Ethnicity is one of the most salient clues to face identity. Analysis of ethnicity-specific facial data is a challenging problem and predominantly carried out using computer-based algorithms. Current published literature focusses on the use of frontal face images. We addressed the challenge of binary (British Pakistani or other ethnicity) ethnicity classification using profile facial images. The proposed framework is based on the extraction of geometric features using 10 anthropometric facial landmarks, within a purpose-built, novel database of 135 multi-ethnic and multi-racial subjects and a total of 675 face images. Image dimensionality was reduced using Principle Component Analysis and Partial Least Square Regression. Classification was performed using Linear Support Vector Machine. The results of this framework are promising with 71.11% ethnic classification accuracy using a PCA algorithm + SVM as a classifier, and 76.03% using PLS algorithm + SVM as a classifier.

KW - machine learning

KW - face identity

KW - ethnic classification

U2 - 10.1109/CW.2017.27

DO - 10.1109/CW.2017.27

M3 - Conference contribution

SP - 170

EP - 173

BT - 2017 International Conference on Cyberworlds (CW)

PB - IEEE

ER -

Jilani SK, Ugail H, Bukar AM, Logan A, Munshi T. A machine learning approach for ethnic classification: the British Pakistani face. In 2017 International Conference on Cyberworlds (CW). IEEE. 2017. p. 170-173 https://doi.org/10.1109/CW.2017.27