SIFT Feature-Based Second-Order Image Hash Retrieval Approach
Xianghui Zhao, Zhirong Li, Junkai Yi · Journal of Software · 2018
In this paper, a second-order Hash retrieval approach is proposed based on SIFT feature of pictures and applied to search similar images.Firstly, extract features of an image by the method of SIFT.Then, cluster the key words through K-Means algorithm and create a word frequency table of the features by utilizing bag of word algorithm.Finally, match familiar images by the method of second-order Hash retrieval algorithm based on the word frequency table.The second-order Hash retrieval algorithm includes two steps.The first-order Hash retrieval aims to search similarities of feature distribution structure.And the second-order Hash retrieval implements accurate search, which depends on the ratio of the quantity of the two images' features belong to the same feature category to the total feature points of the image itself.The experiment results indicate that this approach performs well on accuracy and efficiency.