Gender Recognition Using Cognitive Modeling

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Standard

Gender Recognition Using Cognitive Modeling. / Fagertun, Jens; Andersen, Tobias; Paulsen, Rasmus Reinhold.

Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. Springer, 2012. p. 300-308 (Lecture Notes in Computer Science, Vol. 7584).

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Harvard

Fagertun, J, Andersen, T & Paulsen, RR 2012, 'Gender Recognition Using Cognitive Modeling'. in Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. Springer, pp. 300-308. Lecture Notes in Computer Science, vol. 7584, , 10.1007/978-3-642-33868-7_30

APA

Fagertun, J., Andersen, T., & Paulsen, R. R. (2012). Gender Recognition Using Cognitive Modeling. In Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. (pp. 300-308). Springer. (Lecture Notes in Computer Science, Vol. 7584). 10.1007/978-3-642-33868-7_30

CBE

Fagertun J, Andersen T, Paulsen RR. 2012. Gender Recognition Using Cognitive Modeling. In Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. Springer. pp. 300-308. (Lecture Notes in Computer Science, Vol. 7584). Available from: 10.1007/978-3-642-33868-7_30

MLA

Fagertun, Jens, Tobias Andersen, and Rasmus Reinhold Paulsen "Gender Recognition Using Cognitive Modeling". Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. Springer. 2012. 300-308. (Lecture Notes in Computer Science, Volume 7584). Available: 10.1007/978-3-642-33868-7_30

Vancouver

Fagertun J, Andersen T, Paulsen RR. Gender Recognition Using Cognitive Modeling. In Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. Springer. 2012. p. 300-308. (Lecture Notes in Computer Science, Vol. 7584). Available from: 10.1007/978-3-642-33868-7_30

Author

Fagertun, Jens; Andersen, Tobias; Paulsen, Rasmus Reinhold / Gender Recognition Using Cognitive Modeling.

Computer Vision – ECCV 2012: Workshops and Demonstrations, Part II. Springer, 2012. p. 300-308 (Lecture Notes in Computer Science, Vol. 7584).

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Bibtex

@inbook{94435444c5da4d91aa40ff3a185bfcec,
title = "Gender Recognition Using Cognitive Modeling",
keywords = "Gender recognition, Linear Discriminant Analysis, Support Vector Machines, Cognitive Modeling, Linear Regression",
publisher = "Springer",
author = "Jens Fagertun and Tobias Andersen and Paulsen, {Rasmus Reinhold}",
year = "2012",
doi = "10.1007/978-3-642-33868-7_30",
isbn = "978-3-642-33867-0",
series = "Lecture Notes in Computer Science",
pages = "300-308",
booktitle = "Computer Vision – ECCV 2012",

}

RIS

TY - GEN

T1 - Gender Recognition Using Cognitive Modeling

A1 - Fagertun,Jens

A1 - Andersen,Tobias

A1 - Paulsen,Rasmus Reinhold

AU - Fagertun,Jens

AU - Andersen,Tobias

AU - Paulsen,Rasmus Reinhold

PB - Springer

PY - 2012

Y1 - 2012

N2 - In this work, we use cognitive modeling to estimate the ”gender strength” of frontal faces, a continuous class variable, superseding the traditional binary class labeling. To incorporate this continuous variable we suggest a novel linear gender classification algorithm, the Gender Strength 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. Also the human performance of known data sets is reported, and surprisingly it seems to be quite a hard task for humans. Finally our results are reproduced on a data set of above 40,000 public Danish LinkedIN profile pictures.

AB - In this work, we use cognitive modeling to estimate the ”gender strength” of frontal faces, a continuous class variable, superseding the traditional binary class labeling. To incorporate this continuous variable we suggest a novel linear gender classification algorithm, the Gender Strength 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. Also the human performance of known data sets is reported, and surprisingly it seems to be quite a hard task for humans. Finally our results are reproduced on a data set of above 40,000 public Danish LinkedIN profile pictures.

KW - Gender recognition

KW - Linear Discriminant Analysis

KW - Support Vector Machines

KW - Cognitive Modeling

KW - Linear Regression

U2 - 10.1007/978-3-642-33868-7_30

DO - 10.1007/978-3-642-33868-7_30

SN - 978-3-642-33867-0

BT - Computer Vision – ECCV 2012

T2 - Computer Vision – ECCV 2012

T3 - Lecture Notes in Computer Science

T3 - en_GB

SP - 300

EP - 308

ER -