Creating efficient codebooks for visual recognition

Creating efficient codebooks for visual recognition (2005)

Cached

Download Links

[lear.inrialpes.fr]

Other Repositories/Bibliography

DBLP

by Frederic Jurie , Bill Triggs

Venue:	In Proceedings of the IEEE International Conference on Computer Vision
Citations:	111 - 12 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Creating efficient codebooks for visual recognition	INFERENCE
AUTHOR NAME	Frederic Jurie	SVM HeaderParse 0.2
AUTHOR ADDR	GRAVIR-INRIA-CNRS, 655 Avenue de l’Europe, Montbonnot 38330, France	SVM HeaderParse 0.2
AUTHOR NAME	Bill Triggs	SVM HeaderParse 0.2
AUTHOR ADDR	GRAVIR-INRIA-CNRS, 655 Avenue de l’Europe, Montbonnot 38330, France	SVM HeaderParse 0.2
ABSTRACT	Visual codebook based quantization of robust appearance descriptors extracted from local image patches is an effective means of capturing image statistics for texture analysis and scene classification. Codebooks are usually constructed by using a method such as k-means to cluster the descriptor vectors of patches sampled either densely (‘textons’) or sparsely (‘bags of features ’ based on keypoints or salience measures) from a set of training images. This works well for texture analysis in homogeneous images, but the images that arise in natural object recognition tasks have far less uniform statistics. We show that for dense sampling, k-means over-adapts to this, clustering centres almost exclusively around the densest few regions in descriptor space and thus failing to code other informative regions. This gives suboptimal codes that are no better than using randomly selected centres. We describe a scalable acceptance-radius based clusterer that generates better codebooks and study its performance on several image classification tasks. We also show that dense representations outperform equivalent keypoint based ones on these tasks and that SVM or Mutual Information based feature selection starting from a dense codebook further improves the performance. 1.	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	In Proceedings of the IEEE International Conference on Computer Vision	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	29 found	ParsCit 1.0