Multi-class SVMs for Image Classification using Feature Tracking

Graf, ABA; Wallraven, C

Datensatz

DATENSATZ AKTIONENEXPORT

DownloadE-Mail

Bitte beachten Sie, dass eine neuere Version dieses Datensatzes verfügbar ist:
https://pure.mpg.de/pubman/item/item_1792794_2

DetailsÜbersicht

Multi-class SVMs for Image Classification using Feature Tracking

Graf, A., & Wallraven, C.(2002). Multi-class SVMs for Image Classification using Feature Tracking (99).

Item is Freigegeben

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:

Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-DF40-F Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-DF41-D

Genre: Bericht

ausblenden:

Urheber:
Graf, ABA^{1, 2}, Autor
Wallraven, C², Autor

Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795
2Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797

Inhalt

einblenden:

ausblenden:

Schlagwörter: -

Zusammenfassung: In this paper a novel representation for image classification is proposed which exploits the temporal information inherent in natural visual input. Image sequences are represented by a set of salient features which are found by tracking of visual features. In the context of a multi-class classification problem this representation is compared against a representation using only raw image data. The dataset consists of image sequences generated from a processed version of the MPI face database. We consider two types of multi-class SVMs and benchmark them against nearest-neighbor classifiers. By introducing a new set of SVM kernel functions we show that the feature representation significantly outperforms the view representation.