An integrated approach to classify gender and ethnicity

Azher Uddin; Shayhan Ameen Chowdhury

doi:10.1109/ICISET.2016.7856480

An integrated approach to classify gender and ethnicity

Azher Uddin, Shayhan Ameen Chowdhury

School of Mathematical & Computer Sciences

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

3 Citations (Scopus)

Abstract

Faces express many social indications, including gender, ethnicity, age, expression and identity, most of them have drawn thriving attention from various research communities, for instance neuroscience, computer science and psychology. In this paper, we propose a new approach to classify gender and ethnicity by merging both texture and shape features extracted from face images. Gabor filter is used to extract the texture features and histogram of oriented gradients (HOG) is used to extract the shape features from face images. In order to achieve higher performance we combined both texture and shape features. After combining, the size of feature vector obtained is in a high dimension, to decrease the dimensionality Kernel PCA has been implemented. Finally, to classify the gender and ethnicity we used Support Vector Machine. The experimental result shows the effectiveness of proposed framework.

Original language	English
Title of host publication	2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016
Publisher	IEEE
ISBN (Electronic)	9781509061228
DOIs	https://doi.org/10.1109/ICISET.2016.7856480
Publication status	Published - 16 Feb 2017
Event	2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016 - Dhaka, Bangladesh Duration: 28 Oct 2016 → 29 Oct 2016

Conference

Conference	2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016
Country/Territory	Bangladesh
City	Dhaka
Period	28/10/16 → 29/10/16

Keywords

Ethnicity recognition
Gabor filter
Gender recognition
Histogram of oriented gradients
Kernel PCA
Support vector machine

ASJC Scopus subject areas

Hardware and Architecture
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/ICISET.2016.7856480

Cite this

@inproceedings{2a13e662338d4a5b8bbb07ce6eeb29cb,

title = "An integrated approach to classify gender and ethnicity",

abstract = "Faces express many social indications, including gender, ethnicity, age, expression and identity, most of them have drawn thriving attention from various research communities, for instance neuroscience, computer science and psychology. In this paper, we propose a new approach to classify gender and ethnicity by merging both texture and shape features extracted from face images. Gabor filter is used to extract the texture features and histogram of oriented gradients (HOG) is used to extract the shape features from face images. In order to achieve higher performance we combined both texture and shape features. After combining, the size of feature vector obtained is in a high dimension, to decrease the dimensionality Kernel PCA has been implemented. Finally, to classify the gender and ethnicity we used Support Vector Machine. The experimental result shows the effectiveness of proposed framework.",

keywords = "Ethnicity recognition, Gabor filter, Gender recognition, Histogram of oriented gradients, Kernel PCA, Support vector machine",

author = "Azher Uddin and Chowdhury, {Shayhan Ameen}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016 ; Conference date: 28-10-2016 Through 29-10-2016",

year = "2017",

month = feb,

day = "16",

doi = "10.1109/ICISET.2016.7856480",

language = "English",

booktitle = "2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - An integrated approach to classify gender and ethnicity

AU - Uddin, Azher

AU - Chowdhury, Shayhan Ameen

PY - 2017/2/16

Y1 - 2017/2/16

N2 - Faces express many social indications, including gender, ethnicity, age, expression and identity, most of them have drawn thriving attention from various research communities, for instance neuroscience, computer science and psychology. In this paper, we propose a new approach to classify gender and ethnicity by merging both texture and shape features extracted from face images. Gabor filter is used to extract the texture features and histogram of oriented gradients (HOG) is used to extract the shape features from face images. In order to achieve higher performance we combined both texture and shape features. After combining, the size of feature vector obtained is in a high dimension, to decrease the dimensionality Kernel PCA has been implemented. Finally, to classify the gender and ethnicity we used Support Vector Machine. The experimental result shows the effectiveness of proposed framework.

AB - Faces express many social indications, including gender, ethnicity, age, expression and identity, most of them have drawn thriving attention from various research communities, for instance neuroscience, computer science and psychology. In this paper, we propose a new approach to classify gender and ethnicity by merging both texture and shape features extracted from face images. Gabor filter is used to extract the texture features and histogram of oriented gradients (HOG) is used to extract the shape features from face images. In order to achieve higher performance we combined both texture and shape features. After combining, the size of feature vector obtained is in a high dimension, to decrease the dimensionality Kernel PCA has been implemented. Finally, to classify the gender and ethnicity we used Support Vector Machine. The experimental result shows the effectiveness of proposed framework.

KW - Ethnicity recognition

KW - Gabor filter

KW - Gender recognition

KW - Histogram of oriented gradients

KW - Kernel PCA

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85015871230&partnerID=8YFLogxK

U2 - 10.1109/ICISET.2016.7856480

DO - 10.1109/ICISET.2016.7856480

M3 - Conference contribution

AN - SCOPUS:85015871230

BT - 2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016

PB - IEEE

T2 - 2016 International Conference on Innovations in Science, Engineering and Technology, ICISET 2016

Y2 - 28 October 2016 through 29 October 2016

ER -

An integrated approach to classify gender and ethnicity

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this