ImSe: Exploratory time-efficient image retrieval system

Ksenia Konyushkova*, Dorota Głowacka

*Corresponding author for this work

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

Abstract

We consider the problem of Content-Based Image Retrieval (CBIR) with interactive user feedback when the user is unable to query the system with natural language text. We employ content-based techniques with Relevance Feedback mechanism to capture the precise need of the user and interactively refine the query. We apply the Exploration/Exploitation trade-off with Hierarchical Gaussian Process Bandits and pseudo feedback in order to tackle the problem of optimization in face of uncertainty and to improve the quality of multiple images selection. We tackle the scalability issue with Self-Organizing Map as a preprocessing techniques. A prototype system called ImSe was developed and tested in experiments with real users in different types of search tasks. The experiments show favorable results and indicate the benefits of proposed aprroach.

Original languageEnglish
Title of host publicationInformation Retrieval - 8th Russian Summer School, RuSSIR 2014, Revised Selected Papers
PublisherSpringer Verlag
Pages307-319
Number of pages13
ISBN (Print)9783319254845
DOIs
Publication statusPublished - 2015
MoE publication typeA4 Article in a conference publication
EventRussian Summer School in Information Retrieval - Nizhny Novgorod, Russian Federation
Duration: 18 Aug 201422 Aug 2014
Conference number: 8

Publication series

NameCommunications in Computer and Information Science
Volume505
ISSN (Print)18650929

Seminar

SeminarRussian Summer School in Information Retrieval
Abbreviated titleRuSSIR
CountryRussian Federation
CityNizhny Novgorod
Period18/08/201422/08/2014

Keywords

  • Content-based image retrieval
  • Exploration/Exploitation
  • Gaussian process bandits
  • Relevance feedback
  • Self-organizing maps

Fingerprint Dive into the research topics of 'ImSe: Exploratory time-efficient image retrieval system'. Together they form a unique fingerprint.

Cite this