Abstract | ||
---|---|---|
One of the main challenges for Content-Based Image Retrieval (CBIR) is to achieve meaningful mappings between the high-level semantic concepts and the low-level visual features in images. This paper presents an approach for bridging this semantic gap to improve retrieval quality using the Ranking Support Vector Machine (Ranking SVM) algorithm. Ranking SVM is a supervised learning algorithm which models the relationship between semantic concepts and image features, and performs retrieval at the semantic level. We apply it to the problem of vertebra shape retrieval on a digitized spine x-ray image collection from the second National Health and Nutrition Examination Survey (NHANES II). The experimental results show that the retrieval precision is improved 2.45-15.16% using the proposed approach. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ISBI.2009.5193057 | ISBI |
Keywords | Field | DocType |
digitized spine x-ray image,high-level semantic concept,ranking svm,retrieval quality,vertebra shape retrieval,image retrieval,ranking support,retrieval precision,semantic gap,semantic level,semantic concept,support vector machines,shape,learning artificial intelligence,supervised learning,biomedical imaging,image features,support vector machine,data mining,feature extraction,spine | Computer vision,Ranking,Pattern recognition,Ranking SVM,Computer science,Support vector machine,Semantic gap,Image retrieval,Feature extraction,Artificial intelligence,Content-based image retrieval,Visual Word | Conference |
Citations | PageRank | References |
1 | 0.36 | 9 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haiying Guan | 1 | 81 | 8.98 |
Sameer Antani | 2 | 1402 | 134.03 |
L. Rodney Long | 3 | 534 | 56.98 |
George R. Thoma | 4 | 1207 | 132.81 |