基于哈希技术的BoVW图像检索  

Image Retrieval Based on BoVW and Hashing

作　　者：代雪梅[1,2] 李生刚[1] 

机构地区：[1]陕西师范大学数学与信息科学学院,陕西西安710062 [2]青海师范大学数学系,青海西宁810008

出　　处：《微电子学与计算机》2016年第12期11-14,19,共5页Microelectronics & Computer

基　　金：国家自然科学基金(11071151)

摘　　要：本文提出了一种基于哈希技术的BoVW图像检索方法.选择合适的生成二进制哈希码的哈希算法,将局部特征点保持相似性地映射为二进制哈希码.再在二进制哈希码上进行k-means,生成视觉词为二进制码的视觉词典.最后,用视觉单词的词频向量表示图像内容,并根据词频向量对图像进行检索.实验结果表明,该方法可以缩短视觉词典生成的时间,占用更少的存储空间.Currently, this paper propose an image retrieval method based on BoVW and hashing. Firstly, select an appropriate binary hashing algorithm, which map the similar local feature points into similar binary hash codes. Second, play k-means on the binary hash codes and generate the visual vocabulary with binary visual word. Finally, the image is represented with the word frequency vector of visual words, and image retrieval is achieved based on the word frequency vector. Experimental results on SIFT-1M and Caltech-256 data sets show that the proposed method can reduce the visual vocabulary generation time and take up less storage space.

关 键 词：二进制哈希码 视觉词袋模型 二进制视觉词典 图像检索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]