Abstract | ||
---|---|---|
A unified medical image retrieval framework integrating visual and text keywords using a novel multi-modal query expansion (QE) is presented. For the content-based image search, visual keywords are modeled using support vector machine (SVM)-based classification of local color and texture patches from image regions. For the text-based search, keywords from the associated annotations are extracted and indexed. The correlations between the keywords in both the visual and text feature spaces are analyzed for QE by considering local feedback information. The QE approach can propagate user perceived semantics from one modality to another and improve retrieval effectiveness when combined in multi-modal search. An evaluation of the method on imageCLEFmed'08 dataset and topics results in a mean average precision (MAP) score of 0.15 over comparable searches without QE or using only single modality. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-11769-5_11 | MCBR-CDS |
Keywords | Field | DocType |
local analysis,qe approach,local feedback information,image region,content-based image search,local color,visual keyword,unified medical image retrieval,text-based search,multi-modal search,multi-modal query expansion,comparable search,feature space,indexation,query expansion,mean average precision,support vector machine | Web search query,Automatic image annotation,Query expansion,Information retrieval,Computer science,Support vector machine,Image retrieval,Modal,Semantics,Visual Word | Conference |
Volume | ISSN | ISBN |
5853 | 0302-9743 | 3-642-11768-6 |
Citations | PageRank | References |
6 | 0.51 | 14 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Md. Mahmudur Rahman | 1 | 652 | 50.91 |
Sameer Antani | 2 | 1402 | 134.03 |
L. Rodney Long | 3 | 534 | 56.98 |
Dina Demner Fushman | 4 | 1717 | 147.70 |
George R. Thoma | 5 | 1207 | 132.81 |