互联网 qkzz.net
全刊杂志网:首页 > 女性 > 文章正文
刊社推荐

一种基于MD5的近似图像检测算法研究叶志伟 夏 彬 王大震 张彦超


摘 要:在WWW图像搜索引擎中,如何快速而准确地检测出近似或重复图像已经成为亟待解决的问题,提出一种基于MD5的近似图像检测算法。该算法选取图像分块灰度均值为特征,经过拉普拉斯特征值降维,矢量量化后,图像特征被转换为MD5值,然后根据生成的MD5值进行近似或重复图像检测。实验结果表明该算法是有效的。
  关键词:图像检索; 近似图像; MD5; 拉普拉斯特征值降维
  中图法分类号:TP391
  文献标志码:A
  
  文章编号:1001-3695(2010)02-0788-03
  doi:10.3969/j.issn.1001-3695.2010.02.109
  
  Research of similar images detection algorithm based on MD5
  
  YE Zhi-wei1, XIA Bin1, WANG Da-zhen1, ZHANG Yan-chao2
  
  (1. School of Computer Science, Hubei University of Technology, Wuhan 430068, China;
  2 .School of Computer Science, Wuhan University of Technology, Wuhan 430070, China)
  
  Abstract: There are many similar or duplicate images in the World Wide Web, how to efficiently and accurately find those images has become an issue in search engine research area. This paper presented a similar images detection algorithm based on MD5, which selected the average of gray-block for feature. MD5 was generated by the feature after Laplacian eigenmap dimensionality reduction and vector quantization, then it detected the similar or duplicate images by the MD5. Experimental results show that the algorithm is effective.
  Key words: image retrieval; similar image; MD5; Laplacian eigenmap ......
很抱歉,暂无全文,若需要阅读全文或喜欢本刊物请联系《计算机应用研究》杂志社购买。
欢迎作者提供全文,请点击编辑
分享:
 

了解更多资讯,请关注“木兰百花园”
分享:
 
精彩图文


关键字
支持中国杂志产业发展,请购买、订阅纸质杂志,欢迎杂志社提供过刊、样刊及电子版。
关于我们 | 网站声明 | 刊社管理 | 网站地图 | 联系方式 | 中图分类法 | RSS 2.0订阅 | IP查询
全刊杂志赏析网 2017