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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of The First Asian Conference on Pattern Recognition 2011, |
| Number of pages | 5 |
| Publication date | 2011 |
| Pages | 422-426 |
| ISBN (Print) | 978-1-4577-0122-1 |
| ISBN (Electronic) | 978-1-4577-0121-4 |
| DOIs | |
| Publication status | Published - 2011 |
| Event | Asian Conference on Pattern Recognition - Beijing, China Duration: 28 Nov 2011 → 28 Nov 2011 Conference number: 1 |
Conference
| Conference | Asian Conference on Pattern Recognition |
|---|---|
| Number | 1 |
| Country/Territory | China |
| City | Beijing |
| Period | 28/11/2011 → 28/11/2011 |