摘要
针对医学胸部CT扫描图像,在分别研究单一特征检索算法基础上,提出了基于底层—底层和底层—高层两种级别的特征融合检索方法.据此,用VC#和SQL server2005实现了一个图像检索原型系统,验证了所提方法的有效性.
In allusion to chest CT image database,a multi-level feature fusion algorithm including low-low level and low-high level is proposed based on the study of single feature.Then,a prototype system which supports query by example is implemented using VC# and SQL server 2005,and the experimental results shows that the approach is effective.
出处
《南华大学学报（自然科学版）》
2014年第2期76-78,83,共4页
Journal of University of South China：Science and Technology
关键词
医学图像检索
语义信息
多级别特征融合
medical image retrieval
semantic information
multi-level feature fusion
