复杂相似性图像检索系统体系结构

A Retrieval Mechanism for Complex Similarity Queries in Image Databases

研究了一种支持复杂相似性查询的图像检索系统体系结构、提出了处理复杂相似性查询的技术 ,构造出一个高效的图像检索系统 .图像的内容由三种特征来定义 :可量化的可视化信息特征、非量化描述的语义信息特征和包含更抽象语义信息的关键字特征 .用户可以根据上述特征对图像数据库进行各种简单到复杂的查询、利用面向对象的注释描述模型实现图像的高层语义内容索引 。

A contentbased image retrieval mechanism to support complex similarity queries is presented. The image content is defined by three kinds of features: quantifiable features describing the visual information, nonquantifiable features describing the semantic information, and keywords describing more abstract semantic information. Based on these feature sets, users can process from simple to complex similarity queries. Semantic index is created by objectoriented annotation descriptor schema, and visual index is created using quantifiable features extracted from image representation. The techniques for processing complex similarity queries are also provided. These three issues are very important to construct the effective and efficient image retrieval system.