一种由DCT和SURF改进的图像感知哈希算法

An Improved Perceptual Hashing Algorithm of Image Based on Discrete Cosine Transform and Speeded Up Robust Features

针对感知哈希技术中图像全局特征鲁棒性低和局部特征算法复杂度高的特点,提出一种由离散余弦变换(DCT)和SURF算子改进的感知哈希算法.本文以DCT为全局特征,以SURF描述子为局部特征,分别给出了两者的哈希编码算法及两者的融合方式,接着给出在图像认证时的算法流程.实验表明本文算法具有较好的鲁棒性和实时性.

In order to solve the problem of poor robustness of global features and high complexity of local features in image perceptual hashing algorithm,the author proposed an improved perceptual hashing algorithm based on DCT and SURF. Using DCT as global fea- tnres and SURF as local features, the author gave the hashing functions and the fusion of two features. Then, the author provided the application in image authentication. Experimental results showed that this algorithm has good robustness and efficiency.