摘要
在基于内容的图像检索方法中,图像的低级视觉特征和高级语义之间存在着较大的差异,导致检索性能不佳.为了提高检索性能,将相关反馈技术引入图像检索.利用支持向量机在相关反馈的过程中为图像建立语义模型,在建立语义信息后求出图像间的二次距离,增加图像间的语义区分能力,使被检索出的图像在语义上更加接近示例图像.试验表明,该方法使查全率和查准率得到较大提高.
In the approach of content-based image retrieval, the wide semantic gap between low-level features and high-level concept results in the ineffective performance of image retrieval. In order to improve the performance of retrieval, relevance feedback technology has been introduced into image retrieval. In this paper, support vector machines are trained for natural images to build the semantic model for images in the procession of relevance feedback, then the twice distance of images is computed to reinforce the semantic discrimination between images and make the images retrieved more similar to query image from the semantic point. Experimental results show that this approach can improve precision and recall effectively.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2006年第9期1582-1585,共4页
Journal of Harbin Institute of Technology
基金
黑龙江省自然科学基金资助项目(F0324)
关键词
基于内容的图像检索
支持向量机
相关反馈
content-based image retrieval
support vector machine
relevance feedback