多特征迭代哈希

Multiple Feature Iterative Hashing

随着数据量和数据维数的增加,对数据的分类,查询已经越来越重要了。为了更好地对视频、图片、文本等进行检索,哈希方法应运而生。近年已经有很多好的哈希算法,其速度快,适应高维数据,在模式识别,机器学习等方面得到了广泛的应用。现提出了一种新的多特征哈希方法,称为多特征迭代哈希。上述方法既考虑数据单特征上的紧哈希码,也考虑各特征之间的关系对哈希码的影响,并且通过迭代量化,得到了最优的哈希码。实验结果表明,上述方法在精度上优于三种单特征哈希方法。

With the increase of the amount of data and data dimension, classification and query of the data have become increasingly important. In order to retrieve video, images and text better, hash methods have emerged in re- cent years. There have been many good hash algorithms which have been widely applied in pattern recognition and machine learning, because of its high speed and its adaptability for high - dimensional data. This paper proposed a new method about multiple feature hash, called multiple feature iterative hashing （MFIH）. The method considered the compact hash code of the data as a single feature and also the impact of relationships between features as hash codes. Moreover, we obtained optimal hash codes with iterative quantization. Experiments show that our method can achieve better efficiency than other three hash methods of single feature.