Multi-class SVMs for Image Classification using Feature Tracking

Graf, ABA; Wallraven, C

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

報告書

Multi-class SVMs for Image Classification using Feature Tracking

MPS-Authors

/persons/resource/persons83943

Graf, ABA
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84298

Wallraven, C
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

MPIK-TR-99.pdf
(出版社版), 176KB

付随資料 (公開)

There is no public supplementary material available

引用

Graf, A., & Wallraven, C.(2002). Multi-class SVMs for Image Classification using Feature Tracking (99). Tübingen, Germany: Max Planck Institute for Biological Cybernetics.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-DF40-F

要旨

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.