本文已被：浏览 1081次 下载 2739次
Received:February 26, 2015 Revised:April 26, 2015
Received:February 26, 2015 Revised:April 26, 2015
中文摘要: 针对全局灰度直方图缺少空间分布信息和SIFT特征匹配方法准确性不足的问题,提出基于分块的提取图像颜色矩方法,并改进了SIFT特征度量算法.然后将这两种改进算法相结合,并应用于图像检索系统中.实验结果表明,本文提出的算法在图像检索中取得了较好的效果.
Abstract:Global gray-level histogram lacks of spatial information, SIFT feature matching method do not have a high accuracy. In view of the mentioned problems, this paper proposed a method of extracting color moment, and advanced the measuring method of SIFT features. Then combine the two advanced method for image retrieval. The experiment result shows that the algorithm proposed in this paper do a good job in image retrieval.
keywords: image retrieval color moment SIFT feature matching
文章编号： 中图分类号： 文献标志码：
基金项目:福建省自然科学基金(2011J01338);福建省科技厅重点项目(2013H0020)
引用文本：
郑启财,曾智勇,池燕玲.改进的基于颜色和SIFT特征的图像检索方法.计算机系统应用,2015,24(11):129-133
ZHENG Qi-Cai,ZENG Zhi-Yong,CHI Yan-Ling.Advanced Image Retrieval Method Based on Color and SIFT Feature.COMPUTER SYSTEMS APPLICATIONS,2015,24(11):129-133
郑启财,曾智勇,池燕玲.改进的基于颜色和SIFT特征的图像检索方法.计算机系统应用,2015,24(11):129-133
ZHENG Qi-Cai,ZENG Zhi-Yong,CHI Yan-Ling.Advanced Image Retrieval Method Based on Color and SIFT Feature.COMPUTER SYSTEMS APPLICATIONS,2015,24(11):129-133
