Large-scale geo-facial image analysis

Mohammad T. Islam; Connor Greenwell; Richard Souvenir; Nathan Jacobs

doi:10.1186/s13640-015-0070-9

Large-scale geo-facial image analysis

Mohammad T. Islam, Connor Greenwell, Richard Souvenir, Nathan Jacobs

Computer Science

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

While face analysis from images is a well-studied area, little work has explored the dependence of facial appearance on the geographic location from which the image was captured. To fill this gap, we constructed GeoFaces, a large dataset of geotagged face images, and used it to examine the geo-dependence of facial features and attributes, such as ethnicity, gender, or the presence of facial hair. Our analysis illuminates the relationship between raw facial appearance, facial attributes, and geographic location, both globally and in selected major urban areas. Some of our experiments, and the resulting visualizations, confirm prior expectations, such as the predominance of ethnically Asian faces in Asia, while others highlight novel information that can be obtained with this type of analysis, such as the major city with the highest percentage of people with a mustache.

Original language	English
Article number	17
Journal	Eurasip Journal on Image and Video Processing
Volume	2015
Issue number	1
DOIs	https://doi.org/10.1186/s13640-015-0070-9
State	Published - Dec 3 2015

Bibliographical note

Publisher Copyright:
© 2015, Islam et al.

Funding

This work was partially supported by the NSF (CNS-1156822) and DARPA (D11AP00255). Any opinions, findings, conclusions, or recommendations expressed in this material are those of the authors and do not necessarily reflect those of the sponsor. We gratefully acknowledge flickr users ennuiislife, hotlantavoyeur, rocketboom, besighyawn, and scubabix for allowing us to use their images via Creative Commons licenses. See http://cs.uky.edu/~tarik/papers/geofacial/ for additional information regarding the original images.

Funders	Funder number
U.S. Department of Energy Chinese Academy of Sciences Guangzhou Municipal Science and Technology Project Oak Ridge National Laboratory Extreme Science and Engineering Discovery Environment National Science Foundation National Energy Research Scientific Computing Center National Natural Science Foundation of China	1156822
Defense Advanced Research Projects Agency	D11AP00255

Keywords

Faces
Facial attributes
Geolocation
Images

ASJC Scopus subject areas

Signal Processing
Information Systems
Electrical and Electronic Engineering

Access to Document

10.1186/s13640-015-0070-9

Cite this

@article{285c136ddfba40ddafc9243502224cfa,

title = "Large-scale geo-facial image analysis",

abstract = "While face analysis from images is a well-studied area, little work has explored the dependence of facial appearance on the geographic location from which the image was captured. To fill this gap, we constructed GeoFaces, a large dataset of geotagged face images, and used it to examine the geo-dependence of facial features and attributes, such as ethnicity, gender, or the presence of facial hair. Our analysis illuminates the relationship between raw facial appearance, facial attributes, and geographic location, both globally and in selected major urban areas. Some of our experiments, and the resulting visualizations, confirm prior expectations, such as the predominance of ethnically Asian faces in Asia, while others highlight novel information that can be obtained with this type of analysis, such as the major city with the highest percentage of people with a mustache.",

keywords = "Faces, Facial attributes, Geolocation, Images",

author = "Islam, \{Mohammad T.\} and Connor Greenwell and Richard Souvenir and Nathan Jacobs",

note = "Publisher Copyright: {\textcopyright} 2015, Islam et al.",

year = "2015",

month = dec,

day = "3",

doi = "10.1186/s13640-015-0070-9",

language = "English",

volume = "2015",

number = "1",

}

TY - JOUR

T1 - Large-scale geo-facial image analysis

AU - Islam, Mohammad T.

AU - Greenwell, Connor

AU - Souvenir, Richard

AU - Jacobs, Nathan

PY - 2015/12/3

Y1 - 2015/12/3

N2 - While face analysis from images is a well-studied area, little work has explored the dependence of facial appearance on the geographic location from which the image was captured. To fill this gap, we constructed GeoFaces, a large dataset of geotagged face images, and used it to examine the geo-dependence of facial features and attributes, such as ethnicity, gender, or the presence of facial hair. Our analysis illuminates the relationship between raw facial appearance, facial attributes, and geographic location, both globally and in selected major urban areas. Some of our experiments, and the resulting visualizations, confirm prior expectations, such as the predominance of ethnically Asian faces in Asia, while others highlight novel information that can be obtained with this type of analysis, such as the major city with the highest percentage of people with a mustache.

AB - While face analysis from images is a well-studied area, little work has explored the dependence of facial appearance on the geographic location from which the image was captured. To fill this gap, we constructed GeoFaces, a large dataset of geotagged face images, and used it to examine the geo-dependence of facial features and attributes, such as ethnicity, gender, or the presence of facial hair. Our analysis illuminates the relationship between raw facial appearance, facial attributes, and geographic location, both globally and in selected major urban areas. Some of our experiments, and the resulting visualizations, confirm prior expectations, such as the predominance of ethnically Asian faces in Asia, while others highlight novel information that can be obtained with this type of analysis, such as the major city with the highest percentage of people with a mustache.

KW - Faces

KW - Facial attributes

KW - Geolocation

KW - Images

UR - https://www.scopus.com/pages/publications/84934287616

UR - https://www.scopus.com/inward/citedby.url?scp=84934287616&partnerID=8YFLogxK

U2 - 10.1186/s13640-015-0070-9

DO - 10.1186/s13640-015-0070-9

M3 - Article

AN - SCOPUS:84934287616

SN - 1687-5176

VL - 2015

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

IS - 1

M1 - 17

ER -

Large-scale geo-facial image analysis

Abstract

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this