Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Relevance feedback using generalized Bayesian framework with region-based optimization learning.

Chiou-Ting Hsu1, Chuech-Yu Li

  • 1Department of Computer Science, National Tsing Hua University, Taiwan, ROC. cthsu@cs.nthu.edu.tw

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|October 22, 2005
PubMed
Summary
This summary is machine-generated.

This study introduces a Bayesian framework for image retrieval relevance feedback, improving results with a dynamic user model and region-based analysis for more accurate content-based image retrieval.

Related Experiment Videos

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multilinear Graph Embedding: Representation and Regularization for Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2015
Same author

Simultaneous tensor decomposition and completion using factor priors.

IEEE transactions on pattern analysis and machine intelligence·2014
Same author

Ridge network detection in crumpled paper via graph density maximization.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2012
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

Area of Science:

  • Computer Science
  • Information Retrieval
  • Machine Learning

Background:

  • Content-based image retrieval (CBIR) systems often struggle with accurately interpreting user information needs.
  • Relevance feedback mechanisms aim to refine retrieval results based on user input.
  • Existing methods may not adequately adapt to evolving user preferences over time.

Purpose of the Study:

  • To develop a generalized Bayesian framework for relevance feedback in CBIR.
  • To incorporate a time-varying user model to adapt to changing user information needs.
  • To enhance retrieval accuracy by performing feedback at the region level.

Main Methods:

  • A Bayesian learning method is employed for relevance feedback.
  • A user model is defined with a target query and a user conception to capture evolving preferences.
  • Region-level image representation and a region clustering technique are utilized for correspondence.
  • A weighting scheme is formulated for the region-level matching criterion.

Main Results:

  • The proposed time-varying user model significantly improves retrieval performance.
  • Region-based feedback techniques further enhance the accuracy of CBIR.
  • Experimental results demonstrate the effectiveness of the generalized Bayesian framework.

Conclusions:

  • The developed Bayesian framework with a time-varying user model offers a robust approach to relevance feedback.
  • Region-level analysis is crucial for improving the precision of content-based image retrieval.
  • The proposed methods provide a significant advancement in adaptive image retrieval systems.