en
Technical report
Open access
English

Assessing Agreement Between Human and Machine Clusterings of Image Databases

PublisherGenève
Collection
  • Technical report VISION; 97.03
Publication date1997
Abstract

There is currently much interest in the organization and content-based querying image databases. The usual hypothesis is that image similarity can be characterized by low-level features, without further abstraction. This assumes that agreement between machine and human measures of similarity is sufficient for the database to be useful. To assess this assumption, we develop measures of the agreement between partitionings of an image set, showing that chance agreements must be considered. These measures are used to assess the agreement between human subjects and several machine clustering techniques on an image set. The results can be used to select and refine distance measures for querying and organizing image databases.

Keywords
  • image similarity
  • perceptual distance
  • databases
  • query by content
  • clustering
  • reliability
  • espected agreement
Citation (ISO format)
SQUIRE, David, PUN, Thierry. Assessing Agreement Between Human and Machine Clusterings of Image Databases. 1997
Main files (1)
Report
accessLevelPublic
Identifiers
  • PID : unige:48055
473views
198downloads

Technical informations

Creation03/09/2015 11:34:30 AM
First validation03/09/2015 11:34:30 AM
Update time03/14/2023 11:00:39 PM
Status update03/14/2023 11:00:38 PM
Last indexation01/16/2024 5:17:12 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack