A new approach for relevance feedback through positive and negative samples
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 905-908 Vol.4
- https://doi.org/10.1109/icpr.2004.1333919
Abstract
Relevance feedback has recently emerged as a solution to the problem of providing an effective response to a similarity query in an images retrieval system based on low-level information such as color, texture and shape features. This work describes an approach for learning an optimal similarity metric based on the analysis of relevant and non-relevant information given by the user during the feedback process. A positive and a negative space are determined as an approximation of the examples given by the user. The relevant region is represented by a KL subspace of positive examples and is iteratively updated at each feedback iteration. The nonrelevant region is modeled by a MKL space, which better characterizes the variety of negative examples, which very likely could belong to more than one class. The search process is, then, formulated as a classification problem, based on the calculation of the minimal distance to the relevant or non-relevant region.Keywords
This publication has 10 references indexed in Scilit:
- Relevance feedback in content-based image retrieval: bayesian framework, feature subspaces, and progressive learningIEEE Transactions on Image Processing, 2003
- Eigenspace merging for model updatingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Learning from negative example in relevance feedback for content-based image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Efficient query refinement for image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Content-based image retrieval with relevance feedback in MARSPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Boosting image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Optimizing learning in image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- MKL-Tree: A Hierarchical Data Structure for Indexing Multidimensional DataLecture Notes in Computer Science, 2002
- Comparing discriminating transformations and SVM for learning during multimedia retrievalPublished by Association for Computing Machinery (ACM) ,2001
- Multispace KL for pattern representation and classificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001