Large-scale image retrieval with compressed Fisher vectors

The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 3384 - 3391
Main Authors Perronnin, F, Yan Liu, Sánchez, J, Poirier, H
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2010
Subjects
Europe
Helium
Histograms
Image coding
Image retrieval
Image storage
Large-scale systems
Quantization
Random access memory
Vocabulary
Online AccessGet full text

Cover

More Information
Summary:The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by what makes it different from other images. One drawback of the Fisher vector is that it is high-dimensional and, as opposed to the BOV, it is dense. The resulting memory and computational costs do not make Fisher vectors directly amenable to large-scale retrieval. Therefore, we compress Fisher vectors to reduce their memory footprint and speed-up the retrieval. We compare three binarization approaches: a simple approach devised for this representation and two standard compression techniques. We show on two publicly available datasets that compressed Fisher vectors perform very well using as little as a few hundreds of bits per image, and significantly better than a very recent compressed BOV approach.
ISBN:1424469848
9781424469840
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2010.5540009