Multi-feature hashing based on SNR maximization

Honghai Yu, Pierre Moulin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Hashing algorithms which encode signal content into compact binary codes to preserve similarity, have been extensively studied for applications such as large-scale visual search. However, most existing hashing algorithms work with a single feature type, while combining multiple features is helpful in many vision tasks. In this paper, we propose two multi-feature hashing algorithms based on signal-to-noise ratio (SNR) maximization, where a globally optimal solution is obtained by solving a generalized eigenvalue problem. The first one jointly considers all feature correlations and learns uncorrelated hash functions that maximize SNR, and the second algorithm separately learns hash functions on each individual feature and selects the final hash functions based on the SNR associated with each hash function. The proposed algorithms perform favorably compared to other state-of-the-art multi-feature hashing algorithms on several benchmark datasets.

Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PublisherIEEE Computer Society
Pages1815-1819
Number of pages5
ISBN (Electronic)9781479983391
DOIs
StatePublished - Dec 9 2015
EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
Duration: Sep 27 2015Sep 30 2015

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2015-December
ISSN (Print)1522-4880

Other

OtherIEEE International Conference on Image Processing, ICIP 2015
CountryCanada
CityQuebec City
Period9/27/159/30/15

Keywords

  • Hashing
  • multi-feature
  • signal-to-noise ratio

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'Multi-feature hashing based on SNR maximization'. Together they form a unique fingerprint.

Cite this