Bag-of-features based medical image retrieval via multiple assignment and visual words weighting

Handle URI:
http://hdl.handle.net/10754/561909
Title:
Bag-of-features based medical image retrieval via multiple assignment and visual words weighting
Authors:
Wang, Jingyan; Li, Yongping; Zhang, Ying; Wang, Chao; Xie, Honglan; Chen, Guoling; Gao, Xin ( 0000-0002-7108-3574 )
Abstract:
Bag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights. © 2011 IEEE.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Computational Bioscience Research Center (CBRC); Structural and Functional Bioinformatics Group
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Medical Imaging
Issue Date:
Nov-2011
DOI:
10.1109/TMI.2011.2161673
PubMed ID:
21859616
Type:
Article
ISSN:
02780062
Sponsors:
The work was supported by the Major State Basic Research Development Program of China (973 Program) under Grant 2010CB834303 and a grant from King Abdullah University of Science and Technology.
Appears in Collections:
Articles; Structural and Functional Bioinformatics Group; Computer Science Program; Computational Bioscience Research Center (CBRC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorWang, Jingyanen
dc.contributor.authorLi, Yongpingen
dc.contributor.authorZhang, Yingen
dc.contributor.authorWang, Chaoen
dc.contributor.authorXie, Honglanen
dc.contributor.authorChen, Guolingen
dc.contributor.authorGao, Xinen
dc.date.accessioned2015-08-03T09:33:52Zen
dc.date.available2015-08-03T09:33:52Zen
dc.date.issued2011-11en
dc.identifier.issn02780062en
dc.identifier.pmid21859616en
dc.identifier.doi10.1109/TMI.2011.2161673en
dc.identifier.urihttp://hdl.handle.net/10754/561909en
dc.description.abstractBag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights. © 2011 IEEE.en
dc.description.sponsorshipThe work was supported by the Major State Basic Research Development Program of China (973 Program) under Grant 2010CB834303 and a grant from King Abdullah University of Science and Technology.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectBag-of-featuresen
dc.subjectboostingen
dc.subjectmedical image retrievalen
dc.subjectmultiple assignmenten
dc.subjectquadratic programming (QP) problemen
dc.subjectvisual words weightingen
dc.titleBag-of-features based medical image retrieval via multiple assignment and visual words weightingen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentComputational Bioscience Research Center (CBRC)en
dc.contributor.departmentStructural and Functional Bioinformatics Groupen
dc.identifier.journalIEEE Transactions on Medical Imagingen
dc.contributor.institutionShanghai Institute of Applied Physics, Chinese Academy of Science, Shanghai 201800, Chinaen
dc.contributor.institutionOGI School of Science and Engineering, Oregon Health and Science University, Beaverton, OR 97006, United Statesen
dc.contributor.institutionZhongshan Hospital, Fudan University, Shanghai 200032, Chinaen
kaust.authorGao, Xinen

Related articles on PubMed

All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.