Dynamic Exploratory Search in Content-Based Image Retrieval

Joel Pyykkö, Dorota Glowacka

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

Abstract

With the increase of digital media databases, the need for methods that can allow the user to efficiently peruse them has risen dramatically. This paper studies how to explore image datasets more efficiently in online content-based image retrieval (CBIR). We present a new approach for exploratory CBIR that is dynamic, robust and gives a good coverage of the search space, while maintaining a high retrieval precision. Our method uses deep similarity-based learning to find a new representation of the image space. With this metric, it finds the central point of interest and clusters its local region to present the user with representative images within the vicinity of their target search. This clustering provides a more varied training set for the next iteration, allowing the location of relevant features faster. Additionally, relearning a representation of the user’s search interest in each round enables the system to find other non-local regions of interest in the search space, thus preventing the user from getting stuck in a context trap. We test our method in a simulated online setting, taking into consideration the accuracy, coverage and flexibility of adapting to changes in the user’s interest.
Original languageEnglish
Title of host publicationImage Analysis - 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12-14, 2017, Proceedings, Part I
PublisherSpringer, Cham
Pages538-549
Number of pages12
ISBN (Electronic)978-3-319-59126-1
ISBN (Print)978-3-319-59125-4
DOIs
Publication statusPublished - 17 May 2017
EventSCANDINAVIAN CONFERENCE ON IMAGE ANALYSIS - Tromso, Norway
Duration: 12 Jun 201714 Jun 2017
http://scia2017.org/

Publication series

NameLecture Notes in Computer Science
Publisher Springer, Cham
Volume10269
ISSN (Print)0302-9743

Conference

ConferenceSCANDINAVIAN CONFERENCE ON IMAGE ANALYSIS
Abbreviated titleSCIA 2017
CountryNorway
CityTromso
Period12/06/1714/06/17
Internet address

Fingerprint

Dive into the research topics of 'Dynamic Exploratory Search in Content-Based Image Retrieval'. Together they form a unique fingerprint.

Cite this