融合底层、语义特征的医学图像检索算法及实现  

Algorithm and Implementation for Medical Image Retrieval Based on Low Level Semantic Feature Fusion

作　　者：宋卫华[1] 韩静[1] 

机构地区：[1]黄山学院信息工程学院,安徽黄山245041

出　　处：《黄山学院学报》2008年第5期66-69,共4页Journal of Huangshan University

基　　金：安徽省教育厅教学研究基金资助(2007jyxm436)

摘　　要：针对医学胃窥镜图像,在分别研究颜色聚类、语义单一特征检索算法基础上,提出了结合底层颜色和高层语义的特征融合检索算法。并用VC#和SQLserver2000实现了一个图像检索原型系统,论述了系统的结构、特征提取、相似度匹配方法及部分实验结果,实验表明该方法具有良好的检索效果。With reference to endoscopic image database, a new algorithm with multi-feature fusion referring to low-level and high-level aspects is proposed based on the study of single feature including color clustering and semantic information. And a prototype system, being implemented using VC# and SQL server 2000, is introduced with emphasis on the system architecture, feature extraction, similarity measures and some experiment results. The results show that the approach proposed in this paper is effective.

关 键 词：医学图像检索 颜色聚类 高层语义 特征融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]