以本体为核心的图像检索研究  

Research on ontology-cored image retrieval

作　　者：史婷婷[1] 沈玉利[1] 

机构地区：[1]仲恺农业工程学院计算机科学与工程学院,广东广州510225

出　　处：《仲恺农业工程学院学报》2010年第3期61-65,共5页Journal of Zhongkai University of Agriculture and Engineering

基　　金：仲恺农业工程学院校级科研基金(G3081807)资助项目

摘　　要：针对目前图像检索系统较难实现语义检索的问题,提出一种新的以本体为核心的图像检索模型.将通用本体和空间本体相结合描述图像语义,并且基于本体中"Is-A"关系设计相似性度量算法实现语义扩展.初步试验证明了在图像语义检索中此检索模型的可行性和优越性.In order to solve the problem that it was difficult to implement semantic retrieval of image,a novel ontology-cored retrieval model of image was proposed,which was based on generic ontology and spatial ontology to describe semantic information of image.A similarity metric using inter-relationship ＇Is-A＇ in an ontology was used to measure the similarity between the images and query,too.The feasibility and superiority of the model was proved by some related experiments.

关 键 词：基于语义的图像检索 本体 图像语义标注 检索模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]