Learning Local Image Descriptors

DMCA

Learning Local Image Descriptors (2007)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Matthew Brown , Gang Hua , Simon Winder

Venue:	Proc. IEEE Conf. Computer Vision and Pattern Recognition
Citations:	170 - 2 self

BibTeX

@INPROCEEDINGS{Brown07learninglocal,
    author = {Matthew Brown and Gang Hua and Simon Winder},
    title = {Learning Local Image Descriptors},
    booktitle = {Proc. IEEE Conf. Computer Vision and Pattern Recognition},
    year = {2007}
}

OpenURL

Abstract

Abstract—In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction, and make use of discriminant learning techniques such as Linear Discriminant Analysis (LDA) and Powell minimization to solve for the parameters. Using these techniques, we obtain descriptors that exceed state-of-the-art performance with low dimensionality. In addition to new experiments and recommendations for descriptor learning, we are also making available a new and realistic ground truth data set based on multiview stereo data. Index Terms—Image descriptors, local features, discriminative learning, SIFT. Ç 1

Keyphrases

local image descriptor index term image descriptor discriminative learning nonlinear transforms state-of-the-art performance powell minimization realistic ground truth data nearest-neighbor classifier linear discriminant analysis low dimensionality descriptor learning new experiment local feature multiview stereo data building block dimensionality reduction

DMCA