Towards exaggerated image stereotypes

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of The First Asian Conference on Pattern Recognition 2011,
Number of pages5
Publication date2011
ISBN (Print)978-1-4577-0122-1
ISBN (Electronic)978-1-4577-0121-4
Publication statusPublished - 2011
EventAsian Conference on Pattern Recognition - Beijing, China
Duration: 28 Nov 201128 Nov 2011
Conference number: 1


ConferenceAsian Conference on Pattern Recognition

ID: 34480902