Fast Discriminative Visual Codebooks using Randomized Clustering Forests - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Fast Discriminative Visual Codebooks using Randomized Clustering Forests

Bill Triggs
Frédéric Jurie

Résumé

Some of the most effective recent methods for content-based image classification work by extracting dense or sparse local image descriptors, quantizing them according to a coding rule such as k-means vector quantization, accumulating histograms of the resulting “visual word” codes over the image, and classifying these with a conventional classifier such as an SVM. Large numbers of descriptors and large codebooks are needed for good results and this becomes slow using k-means. We introduce Extremely Randomized Clustering Forests – ensembles of randomly created clustering trees – and show that these provide more accurate results, much faster training and testing and good resistance to background clutter in several state-of-the-art image classification tasks.
Fichier principal
Vignette du fichier
MTJ-nips06.pdf (424.27 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00203734 , version 1 (14-01-2008)

Identifiants

  • HAL Id : hal-00203734 , version 1

Citer

F. Moosmann, Bill Triggs, Frédéric Jurie. Fast Discriminative Visual Codebooks using Randomized Clustering Forests. Twentieth Annual Conference on Neural Information Processing Systems (NIPS '06), Dec 2006, Vancouver, Canada. pp.985--992. ⟨hal-00203734⟩
1439 Consultations
1552 Téléchargements

Partager

Gmail Facebook X LinkedIn More