摘要
图像检索是图像数据库的最基本功能,传统检索技术对图像数据库来说存在很大的局限性,图像的检索应采用基于图像内容本身的检索方式,目前流行的各种图像匹配技术主要针对特征明显的图像,需要图像先验知识,缺乏广泛性。分析了传统的模板匹配技术,采用小波变换技术抽取图像低频分量为逻辑对象,利用改进的模板匹配技术进行检索,实验结果表明可大大减少计算量,提高检索效率。
Image searching is the most essential function of the image database. Traditional database searching techniques are very limited for image database. Image Searching should be based on image content, but current various kinds of image matching techniques are mostly suit- able for defferent kinds of images＇ features, which are lack of Extensiveness. This paper analyzed traditional template matching technique, and use wavelet to get lower frequency of image as logic object, and then matching images with improved template matching technique, thus decrease calculating greatly after expriments,
出处
《计算机应用与软件》
CSCD
北大核心
2007年第1期129-131,共3页
Computer Applications and Software
关键词
小波变换
低频
图像检索
模板匹配
Wavelet transform Lower frequency Image searching Template matching
