摘要
提出一种新的基于区域模糊特征的图像检索方法(Region-Based Image Retrieval with Fuzzy Features,RBIRFF).先将图像分割成区域后,利用模糊集理论计算每个区域的模糊特征,再利用区域特征间相似度计算方法,进行图像相似度测量.最后,按照相似度的降序排列图像,得到检索结果.介绍了RBIRFF原型系统的设计和实现,并用实验测评了其检索性能.提出的方法对大型图像数据库的快速和准确检索,有广泛的应用前景.
A novel method, called region-based image retrieval with fuzzy features（RBIRFF）, is introduced, which partitions image into regions firstly, then computes each region fuzzy features with fuzzy set theory, and computes similarities of images. Finally, the retrieval results are obtained. The design and realization of RBIRFF system are also proposed, and its retrieval effectiveness is validated by experiments. This method for image databases efficiency and effectiveness has a wide application.
出处
《郑州大学学报（理学版）》
CAS
2007年第2期122-127,共6页
Journal of Zhengzhou University:Natural Science Edition
基金
湖南省自然科学基金资助项目
编号05JJ40101
关键词
CRIR
模糊集理论
模糊特征
相似度计算
content-region image retrieval
fuzzy set theory
fuzzy features
similarity computation
