Towards exaggerated image stereotypes
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
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. p. 422-426.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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
N1 - Conference code: 1
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,
T2 - Asian Conference on Pattern Recognition
Y2 - 28 November 2011 through 28 November 2011
ER -
ID: 34480902