Metric preserving Dense SIFT compression

Shmuel T. Klein, Dana Shapira

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The problem of compressing a large collection of feature vectors so that object identification can further be processed on the compressed form of the features is investigated. The idea is to perform matching against a query image in the compressed form of the feature descriptor vectors retaining the metric. Given two SIFT feature vectors, in previous work we suggested to compress them using a lossless encoding for which the pairwise matching can be done directly on the compressed files, by means of a Fibonacci code. In this paper we extend our work to Dense SIFT and in particular to PHOW features, that contain, for each image, about 300 times as many vectors as the original SIFT.

Original languageEnglish
Title of host publicationProceedings of the Prague Stringology Conference 2014, PSC 2014
EditorsJan Holub, Jan Zd'arek
Pages139-147
Number of pages9
ISBN (Electronic)9788001055472
StatePublished - 2014
Event18th Prague Stringology Conference, PSC 2014 - Prague, Czech Republic
Duration: 1 Sep 20143 Sep 2014

Publication series

NameProceedings of the Prague Stringology Conference 2014, PSC 2014

Conference

Conference18th Prague Stringology Conference, PSC 2014
Country/TerritoryCzech Republic
CityPrague
Period1/09/143/09/14

Fingerprint

Dive into the research topics of 'Metric preserving Dense SIFT compression'. Together they form a unique fingerprint.

Cite this