Fisher Kernels on Visual Vocabularies for Image Categorization

Within the field of pattern classification, the Fisher kernel is a powerful framework which combines the strengths of generative and discriminative approaches. The idea is to characterize a signal with a gradient vector derived from a generative probability model and to subsequently feed this repres...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2007 IEEE Conference on Computer Vision and Pattern Recognition S. 1 - 8
Hauptverfasser: Perronnin, F., Dance, C.
Format: Tagungsbericht
Sprache:Englisch
Japanisch
Veröffentlicht: IEEE 01.06.2007
Schlagworte:
Character generation
Feeds
Image databases
Kernel
Pattern classification
Power generation
Signal generators
Spatial databases
Visual databases
Vocabulary
ISBN:9781424411795, 1424411793
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Within the field of pattern classification, the Fisher kernel is a powerful framework which combines the strengths of generative and discriminative approaches. The idea is to characterize a signal with a gradient vector derived from a generative probability model and to subsequently feed this representation to a discriminative classifier. We propose to apply this framework to image categorization where the input signals are images and where the underlying generative model is a visual vocabulary: a Gaussian mixture model which approximates the distribution of low-level features in images. We show that Fisher kernels can actually be understood as an extension of the popular bag-of-visterms. Our approach demonstrates excellent performance on two challenging databases: an in-house database of 19 object/scene categories and the recently released VOC 2006 database. It is also very practical: it has low computational needs both at training and test time and vocabularies trained on one set of categories can be applied to another set without any significant loss in performance.
ISBN:9781424411795
1424411793
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2007.383266