3D gender recognition using cognitive modeling

Jens Fagertun; Tobias Andersen; Thomas Hansen; Rasmus Reinhold Paulsen

doi:10.1109/IWBF.2013.6547324

3D gender recognition using cognitive modeling

Jens Fagertun, Tobias Andersen, Thomas Hansen, Rasmus Reinhold Paulsen

Copenhagen University Hospital Herlev and Gentofte

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

We use 3D scans of human faces and cognitive modeling to estimate the “gender strength”. The “gender strength” is a continuous class variable of the gender, superseding the traditional binary class labeling. To visualize some of the visual trends humans use when performing gender classification, we use linear regression. In addition, we use the gender strength to construct a smaller but refined training set, by identifying and removing ill-defined training examples. We use this refined training set to improve the performance of known classification algorithms. Results are presented using a 5-fold cross-validation scheme and also reproduced using an unseen data set.

Original language	English
Title of host publication	2013 International Workshop on Biometrics and Forensics (IWBF)
Number of pages	4
Publisher	IEEE
Publication date	2013
ISBN (Print)	978-1-4673-4987-1
DOIs	https://doi.org/10.1109/IWBF.2013.6547324
Publication status	Published - 2013
Event	2013 International Workshop on Biometrics and Forensics (IWBF) - Lisbon, Portugal Duration: 4 Apr 2013 → 5 Apr 2013 http://www.img.lx.it.pt/iwbf2013/

Workshop

Workshop	2013 International Workshop on Biometrics and Forensics (IWBF)
Country/Territory	Portugal
City	Lisbon
Period	04/04/2013 → 05/04/2013
Internet address	http://www.img.lx.it.pt/iwbf2013/

Access to Document

10.1109/IWBF.2013.6547324

OpenUrl availability

Full text

Cite this

@inproceedings{9f49663204a94b649c1bcb316ae668cd,

title = "3D gender recognition using cognitive modeling",

abstract = "We use 3D scans of human faces and cognitive modeling to estimate the “gender strength”. The “gender strength” is a continuous class variable of the gender, superseding the traditional binary class labeling. To visualize some of the visual trends humans use when performing gender classification, we use linear regression. In addition, we use the gender strength to construct a smaller but refined training set, by identifying and removing ill-defined training examples. We use this refined training set to improve the performance of known classification algorithms. Results are presented using a 5-fold cross-validation scheme and also reproduced using an unseen data set.",

author = "Jens Fagertun and Tobias Andersen and Thomas Hansen and Paulsen, {Rasmus Reinhold}",

year = "2013",

doi = "10.1109/IWBF.2013.6547324",

language = "English",

isbn = "978-1-4673-4987-1 ",

booktitle = "2013 International Workshop on Biometrics and Forensics (IWBF)",

publisher = "IEEE",

address = "United States",

note = "2013 International Workshop on Biometrics and Forensics (IWBF) ; Conference date: 04-04-2013 Through 05-04-2013",

url = "http://www.img.lx.it.pt/iwbf2013/",

}

TY - GEN

T1 - 3D gender recognition using cognitive modeling

AU - Fagertun, Jens

AU - Andersen, Tobias

AU - Hansen, Thomas

AU - Paulsen, Rasmus Reinhold

PY - 2013

Y1 - 2013

N2 - We use 3D scans of human faces and cognitive modeling to estimate the “gender strength”. The “gender strength” is a continuous class variable of the gender, superseding the traditional binary class labeling. To visualize some of the visual trends humans use when performing gender classification, we use linear regression. In addition, we use the gender strength to construct a smaller but refined training set, by identifying and removing ill-defined training examples. We use this refined training set to improve the performance of known classification algorithms. Results are presented using a 5-fold cross-validation scheme and also reproduced using an unseen data set.

AB - We use 3D scans of human faces and cognitive modeling to estimate the “gender strength”. The “gender strength” is a continuous class variable of the gender, superseding the traditional binary class labeling. To visualize some of the visual trends humans use when performing gender classification, we use linear regression. In addition, we use the gender strength to construct a smaller but refined training set, by identifying and removing ill-defined training examples. We use this refined training set to improve the performance of known classification algorithms. Results are presented using a 5-fold cross-validation scheme and also reproduced using an unseen data set.

U2 - 10.1109/IWBF.2013.6547324

DO - 10.1109/IWBF.2013.6547324

M3 - Article in proceedings

SN - 978-1-4673-4987-1

BT - 2013 International Workshop on Biometrics and Forensics (IWBF)

PB - IEEE

T2 - 2013 International Workshop on Biometrics and Forensics (IWBF)

Y2 - 4 April 2013 through 5 April 2013

ER -

3D gender recognition using cognitive modeling

Abstract

Workshop

Access to Document

OpenUrl availability

Fingerprint

Cite this