信息与控制2012，Vol.41Issue(3)：319-325,7.DOI:10.3724/SP.J.1219.2012.00319
一种新的基于本体论描述的内容图像检索模型
A New Model of Content Image Retrieval Based on the Ontology Theory Description
宋广为 1刘程军 1王庆鹏 1叶斌 1潘锋1
作者信息
摘要
Abstract
The problems in the content-based image retrieval are analyzed, and then the ontology theory method is used to build the low-level feature ontology of the image and the special image ontology. Meanwhile, the concept of image descriptor is defined and corresponding image combination rales are setup. At last, the low-level features are selected to retrieve the images, and the multi-class support vector machine (SVM) is chosen to achieve the conjunction between the low-level feature and the high-level description information. Then the semantic retrieval is realized and the influence of the semantic gap problem on the content based image retrieval is reduced. The experiment results show that this model can enhance the precision in content based image retrieval, and it can achieve the semantic retrieval by 3~5 times of feedback.关键词
图像检索/本体/图像描述/多分类支持向量机Key words
image retrieval/ ontology/ image description/ multi-class support vector machine分类
信息技术与安全科学引用本文复制引用
宋广为,刘程军,王庆鹏,叶斌,潘锋..一种新的基于本体论描述的内容图像检索模型[J].信息与控制,2012,41(3):319-325,7.
