以本体为核心的图像情感语义检索模型

Ontology-cored image emotional semantic search model

针对目前图像检索系统较难实现情感语义检索的问题,构建了以本体为核心的图像情感语义检索模型。在对核心本体库的构建中,采用将Mpeg-7和概念格理论与本体构建相结合的方法,其难点在于将Mpeg-7标准描述符与图像情感本体的属性构造的结合,以及自动产生新的概念结果的方法;实现了图像情感领域本体框架的半自动构建。通过系统的初步实现与相关实验的验证,证明了此检索模型在实现图像情感语义检索中的可行性和优越性。

In order to solve the problem that it is difficult to implement emotional semantic search in the course of image searching, an Ontology-cored emotional semantic search model was proposed and constructed. A method combining Mpeg-7, theory of concept lattices and Ontology construction together to construct the kernel Ontology library was put forward. The difficulty of this method lies in integrating the Mpeg-7 standard descriptor with image emotional Ontology properties, as well as auto-generating new concept results, which help the image emotional domain Ontology framework to build semi-automatically. This model was implemented and some related experiments were carried out. Experimental results validate the feasibility and superiority of the model.