首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于MD5的近似图像检测算法研究*
引用本文:叶志伟,夏彬,王大震,张彦超.一种基于MD5的近似图像检测算法研究*[J].计算机应用研究,2010,27(2):788-790.
作者姓名:叶志伟  夏彬  王大震  张彦超
作者单位:(1.湖北工业大学 计算机学院, 武汉 430068; 2.武汉理工大学 计算机学院, 武汉 430070)
基金项目:湖北省教育厅科研项目(Q20081409,Q20081402,Q20081405);湖北省自然科学基金资助项目(2008CDZ003,2008CDB342)
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

Research of similar images detection algorithm based on MD5
YE Zhi-wei,XIA Bin,WANG Da-zhen,ZHANG Yan-chao.Research of similar images detection algorithm based on MD5[J].Application Research of Computers,2010,27(2):788-790.
Authors:YE Zhi-wei  XIA Bin  WANG Da-zhen  ZHANG Yan-chao
Affiliation:(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.
Keywords:image retrieval  similar image  MD5  Laplacian eigenmap
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号