A picture is worth a thousand keywords: Image-based object search on a mobile platform

Tom Yeh, Kristen Grauman, Konrad Tollmar, Trevor Darrell

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

37 Scopus citations

Abstract

Finding information based on an object's visual appearance is useful when specific keywords for the object are not known. We have developed a mobile image-based search system that takes images of objects as queries and finds relevant web pages by matching them to similar images on the web. Image-based search works well when matching full scenes, such as images of buildings or landmarks, and for matching objects when the boundary of the object in the image is available. We demonstrate the effectiveness of a simple interactive paradigm for obtaining a segmented object boundary, and show how a shape-based image matching algorithm can use the object outline to find similar images on the web.

Original languageEnglish
Title of host publicationCHI'05 Extended Abstracts on Human Factors in Computing Systems, CHI EA'05
Pages2025-2028
Number of pages4
DOIs
StatePublished - 2005
EventConference on Human Factors in Computing Systems, CHI EA 2005 - Portland, OR, United States
Duration: 2 Apr 20057 Apr 2005

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Conference

ConferenceConference on Human Factors in Computing Systems, CHI EA 2005
Country/TerritoryUnited States
CityPortland, OR
Period2/04/057/04/05

Keywords

  • Content-based image retrieval
  • Interactive segmentation
  • Mobile interface
  • Object recognition

Fingerprint

Dive into the research topics of 'A picture is worth a thousand keywords: Image-based object search on a mobile platform'. Together they form a unique fingerprint.

Cite this