Towards exaggerated image stereotypes

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 -