一种基于MD5的近似图像检测算法研究

Research of similar images detection algorithm based on MD5

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。

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.