首页 | 本学科首页   官方微博 | 高级检索  
     

基于语义测度的图像相似性计算研究
引用本文:陈久军,肖刚,高飞,张元鸣.基于语义测度的图像相似性计算研究[J].中国图象图形学报,2007,12(10):1877-1880.
作者姓名:陈久军  肖刚  高飞  张元鸣
作者单位:浙江工业大学信息学院 杭州310014
基金项目:国家重点基础研究发展计划(973计划);浙江省科技厅资助项目
摘    要:针对图像检索中的低层视觉特征相似性度量问题,提出一种基于语义测度的图像相似性计算方法。该方法在图像区域分割的基础上,通过构建图像区域子块与语义元数据之间的统计映射关系,实现图像内容的统计语义描述,建立图像之间、图像与语义类别、语义类别之间的分层语义相似测度。通过对自然图像库的实验结果表明,该方法在相似图像检索中具有更好的性能。

关 键 词:语义测度  相似性  图像语义  图像检索
文章编号:1006-8961(2007)10-1877-04
修稿时间:7/5/2007 12:00:00 AM

Research on Image Similarity Calculation Based on Semantic Measure
CHEN Jiu-jun,XIAO Gang,GAO Fei,ZHANG Yuan-ming,CHEN Jiu-jun,XIAO Gang,GAO Fei,ZHANG Yuan-ming,CHEN Jiu-jun,XIAO Gang,GAO Fei,ZHANG Yuan-ming and CHEN Jiu-jun,XIAO Gang,GAO Fei,ZHANG Yuan-ming.Research on Image Similarity Calculation Based on Semantic Measure[J].Journal of Image and Graphics,2007,12(10):1877-1880.
Authors:CHEN Jiu-jun  XIAO Gang  GAO Fei  ZHANG Yuan-ming  CHEN Jiu-jun  XIAO Gang  GAO Fei  ZHANG Yuan-ming  CHEN Jiu-jun  XIAO Gang  GAO Fei  ZHANG Yuan-ming and CHEN Jiu-jun  XIAO Gang  GAO Fei  ZHANG Yuan-ming
Affiliation:College of Information Engineering, Zhejiang University of Technology, Hangzhou 310014
Abstract:In order to solve the problem that the low-level visual features can not express the high-level semantic contents accurately in image retrieval,the paper presents a new image similarity calculating approach using the proposed semantic measure.Based on the segmented image regions,the statistical mapping relationships between image blobs and semantic metadata are constructed and the layered semantic measurements between images are then defined.Experiment results on natural images show good retrieval quality based on the semantic similarity measure method.
Keywords:semantic measure  image similarity  image semantic  image retrieval
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号