机构地区: 湛江海洋大学
出 处: 《情报科学》 2005年第10期1552-1558,共7页
摘 要: 基于内容的图像检索是解决目前图书馆查询大量图片资料的有效方法。本文在研究低层视觉特征提取、高维索引、相似性度量准则与相关反馈技术的基础上,构建了一个高效实用的图书馆图片检索系统,提出了一种颜色特征提取和特征向量的索引方法,对系统的构建方法进行了较详细的讨论。 The method of content-based image retrieval is now an effective method to query a mass of image materials. In this paper, a lot research work has been done around four points: how to abstract low-level feature of vision, how to index in high-dimensional, how to adjusting similarity measure norm and using relevant feedbaek technique. Based on the research work , an efficient and practical image retrieval system of library is built. An index method of abstract the color-feature and feature vectors is proposed, the method of building system is discussed in detail.
领 域: [自动化与计算机技术] [自动化与计算机技术]