Towards exaggerated image stereotypes

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Towards exaggerated image stereotypes. / Chen, Chen; Lauze, Francois Bernard; Igel, Christian; Feragen, Aasa; Loog, Marco; Nielsen, Mads.

Proceedings of The First Asian Conference on Pattern Recognition 2011, . 2011. s. 422-426.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Chen, C, Lauze, FB, Igel, C, Feragen, A, Loog, M & Nielsen, M 2011, Towards exaggerated image stereotypes. i Proceedings of The First Asian Conference on Pattern Recognition 2011, . s. 422-426, Beijing, Kina, 28/11/2011. https://doi.org/10.1109/ACPR.2011.6166569

APA

Chen, C., Lauze, F. B., Igel, C., Feragen, A., Loog, M., & Nielsen, M. (2011). Towards exaggerated image stereotypes. I Proceedings of The First Asian Conference on Pattern Recognition 2011, (s. 422-426) https://doi.org/10.1109/ACPR.2011.6166569

Vancouver

Chen C, Lauze FB, Igel C, Feragen A, Loog M, Nielsen M. Towards exaggerated image stereotypes. I Proceedings of The First Asian Conference on Pattern Recognition 2011, . 2011. s. 422-426 https://doi.org/10.1109/ACPR.2011.6166569

Author

Chen, Chen ; Lauze, Francois Bernard ; Igel, Christian ; Feragen, Aasa ; Loog, Marco ; Nielsen, Mads. / Towards exaggerated image stereotypes. Proceedings of The First Asian Conference on Pattern Recognition 2011, . 2011. s. 422-426

Bibtex

@inproceedings{7bf33c4eca284428be205adda291f298,
title = "Towards exaggerated image stereotypes",
abstract = "Given a training set of images and a binary classifier,we introduce the notion of an exaggerated image stereotype forsome image class of interest, which emphasizes/exaggerates thecharacteristic patterns in an image and visualizes which visualinformation the classification relies on. This is useful for gaininginsight into the classification mechanism. The exaggerated imagestereotypes results in a proper trade-off between classificationaccuracy and likelihood of being generated from the class ofinterest. This is done by optimizing an objective function whichconsists of a discriminative term based on the classificationresult, and a generative term based on the assumption ofthe class distribution. We use this idea with Fisher’s LinearDiscriminant rule, and assume a multivariate normal distributionfor samples within a class. The proposed framework has beenapplied on handwritten digit data, illustrating specific featuresdifferentiating digits. Then it is applied to a face dataset usingActive Appearance Model (AAM), where male faces stereotypesare evolved from initial female faces.",
author = "Chen Chen and Lauze, {Francois Bernard} and Christian Igel and Aasa Feragen and Marco Loog and Mads Nielsen",
year = "2011",
doi = "10.1109/ACPR.2011.6166569",
language = "English",
isbn = "978-1-4577-0122-1",
pages = "422--426",
booktitle = "Proceedings of The First Asian Conference on Pattern Recognition 2011,",

}

RIS

TY - GEN

T1 - Towards exaggerated image stereotypes

AU - Chen, Chen

AU - Lauze, Francois Bernard

AU - Igel, Christian

AU - Feragen, Aasa

AU - Loog, Marco

AU - Nielsen, Mads

PY - 2011

Y1 - 2011

N2 - Given a training set of images and a binary classifier,we introduce the notion of an exaggerated image stereotype forsome image class of interest, which emphasizes/exaggerates thecharacteristic patterns in an image and visualizes which visualinformation the classification relies on. This is useful for gaininginsight into the classification mechanism. The exaggerated imagestereotypes results in a proper trade-off between classificationaccuracy and likelihood of being generated from the class ofinterest. This is done by optimizing an objective function whichconsists of a discriminative term based on the classificationresult, and a generative term based on the assumption ofthe class distribution. We use this idea with Fisher’s LinearDiscriminant rule, and assume a multivariate normal distributionfor samples within a class. The proposed framework has beenapplied on handwritten digit data, illustrating specific featuresdifferentiating digits. Then it is applied to a face dataset usingActive Appearance Model (AAM), where male faces stereotypesare evolved from initial female faces.

AB - Given a training set of images and a binary classifier,we introduce the notion of an exaggerated image stereotype forsome image class of interest, which emphasizes/exaggerates thecharacteristic patterns in an image and visualizes which visualinformation the classification relies on. This is useful for gaininginsight into the classification mechanism. The exaggerated imagestereotypes results in a proper trade-off between classificationaccuracy and likelihood of being generated from the class ofinterest. This is done by optimizing an objective function whichconsists of a discriminative term based on the classificationresult, and a generative term based on the assumption ofthe class distribution. We use this idea with Fisher’s LinearDiscriminant rule, and assume a multivariate normal distributionfor samples within a class. The proposed framework has beenapplied on handwritten digit data, illustrating specific featuresdifferentiating digits. Then it is applied to a face dataset usingActive Appearance Model (AAM), where male faces stereotypesare evolved from initial female faces.

U2 - 10.1109/ACPR.2011.6166569

DO - 10.1109/ACPR.2011.6166569

M3 - Article in proceedings

SN - 978-1-4577-0122-1

SP - 422

EP - 426

BT - Proceedings of The First Asian Conference on Pattern Recognition 2011,

ER -

ID: 34480902