基于内容的图像检索中SS-树索引的Java实现  

Realization of the SS-tree Index in Content-Based Image Retrieval Using Java

作　　者：陈冬霞[1] 吉根林[1] 方昭辉[1] 

机构地区：[1]南京师范大学数学与计算机科学学院,江苏南京210097

出　　处：《南京师范大学学报（工程技术版）》2005年第4期53-56,81,共5页Journal of Nanjing Normal University(Engineering and Technology Edition)

摘　　要：为了提高基于内容图像检索的效率,设计引入空间索引.SS-树索引是常用的空间数据索引,具有平衡性、动态性、构造和维护的简单性,用Java实现了SS-树索引,并在自行开发的基于内容图像检索实验原型系统IRS中使用.给出了SS-树索引文件和类的定义,介绍了主要操作和对应的算法实现.将SS-树索引用于基于内容图像检索的相似性检索,比较了顺序扫描和采用R-树、SS-树进行检索的效率,实验结果表明采用SS-树索引进行基于内容的图像检索是高效可行的.To improve the efficiency of the CBIR,the spatial index is needed . The SS-tree index is the popular spatial index, and has the characteristics of balance and dynamic, and it＇ s easy to construct and maintain. A web-based CBIR system named IRS is realized by using Java, for which the SS-tree indexes are realized. The index documents and the definition of classes are proposed, and the main operation and the corresponding arithmetic are introduced. SS - tree index is used in the comparability index of content image retrieval. The efficiency of order scanning is com- pared with that of retrieving with R-tree and SS-tree. The experiment shows that with the use of index, the efficiency of CBIR is greatly improved. Using SS-tree index to retrieve is efficient and effective for CBIR.

关 键 词：基于内容的图像检索 JAVA SS-树 索引 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]