• Home
  • Search
  • Learning Pathological Characteristics from User's Relevance Feedback for Content-Based Mammogram Retrieval
  • Cite Icon4
  • https://doi.org/10.1109/ism.2006.101Copy DOI Icon

Learning Pathological Characteristics from User's Relevance Feedback for Content-Based Mammogram Retrieval

  • Dec 1, 2006
  • Chia-Hung Wei +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Content-based image retrieval (CBIR) has been proposed to address the problem of image retrieval from medical image databases. Relevance feedback, explaining the user's query concept, can be used to bridge the semantic gap and improve the performance of CBIR systems. This paper proposes a learning method for relevance feedback, which utilizes probabilistic model to generalize the 2-class problem and provide an estimate of probability of class membership. To build the probabilistic model, support vector machine (SVM) is applied to classify the mammograms, and then scale them to the probability of class membership. Experimental results show that the proposed learning method can effectively improve the average precision rate from 40% to 62% through five iterations of relevance feedback rounds

Similar Papers
  • Conference Article
  • Citations7

An user preference information based kernel for SVM active learning in content-based image retrieval

  • Oct 15, 2004
  • Hua Xie +1
  • Research Article
  • Citations17

Adaptive learning for relevance feedback: application to digital mammography.

  • Jul 29, 2010
  • Medical Physics
  • Jung Hun Oh +2
  • Research Article
  • Citations40

Active SVM-based relevance feedback using multiple classifiers ensemble and features reweighting

  • Jun 25, 2012
  • Engineering Applications of Artificial Intelligence
  • Xiang-Yang Wang +2
  • Book Chapter
  • Citations3

Content Analysis from User's Relevance Feedback for Content-Based Image Retrieval

  • Jan 01, 2009
  • Chia-Hung Wei +1
  • Conference Article
  • Citations3

A Semi-Supervised Learning Based Relevance Feedback Algorithm in Content-Based Image Retrieval

  • Oct 01, 2008
  • Zhi-Ping Luo +1
  • Research Article
  • Citations26

Ensemble one-class support vector machines for content-based image retrieval

  • May 17, 2008
  • Expert Systems with Applications
  • Roung-Shiunn Wu +1
  • Conference Article
  • Citations1392

Support vector machine active learning for image retrieval

  • Oct 01, 2001
  • Simon Tong +1
  • Conference Article
  • Citations3

Unbalanced learning in content-based image classification and retrieval

  • Jul 01, 2010
  • Luca Piras +1
  • Book Chapter
  • Citations13

Content-Based Remote Sensing Image Retrieval Using Image Multi-feature Combination and SVM-Based Relevance Feedback

  • Jan 01, 2012
  • Lijun Zhao +5
  • Book Chapter
  • Citations2

Improvement of Reuse of Classifiers in CBIR Using SVM Active Learning

  • Jan 01, 2010
  • Masaaki Tekawa +1
  • Conference Article
  • Citations4

Leveraging non-relevant images to enhance image retrieval performance

  • Dec 01, 2002
  • Ashwin T +2
  • Conference Article
  • Citations1

Biased support vector machine active learning for 3D model retrieval

  • Jun 01, 2010
  • Zhang Zhi-Yong +2
  • Research Article
  • Citations41

A new query reweighting method for document retrieval based on genetic algorithms

  • Oct 01, 2006
  • IEEE Transactions on Evolutionary Computation
  • Yu-Chuan Chang +1
  • Conference Article
  • Citations4

Semantic image retrieval using relevance feedback and reinforcement learning algorithm

  • Sep 01, 2010
  • Zahra Shoaie +1
  • Conference Article
  • Citations3

Content based Image Retrieval with Rocchio Algorithm for Relevance Feedback Using 2D Image Feature Representation

  • Sep 18, 2019
  • Indah Agustien Siradjuddin +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.