基于多视觉词典的显著性加权图像检索方法  

Image Retrieval Based on Saliency Weighted for Multiple Visual Dictionaries

作　　者：孔超[1,2,3] 张化祥[1,3] 生海迪 Kong Chao Zhang Huaxiang Sheng Haidi(School of Information Science ＆ Engineering, Shandong Normal University, Jinan, 250014, China State Grid of China Technology, Jinan, 250002, China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology, Jinan, 250014, China)

机构地区：[1]山东师范大学信息科学与工程学院,济南250014 [2]国网技术学院,济南250002 [3]山东省分布式计算机软件新技术重点实验室,济南250014

出　　处：《数据采集与处理》2017年第2期399-407,共9页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61170145;61373081)资助项目;教育部博士点基金(20113704110001)资助项目;山东省科技攻关计划(2013GGX10125)资助项目

摘　　要：针对视觉词典在图像表示与检索方面的应用需求,本文提出了一种基于多视觉词典与显著性加权相结合的图像检索方法,实现了图像多特征的显著性稀疏表示。该方法首先划分图像为小块,提取图像块的多种底层特征,然后将其作为输入向量,通过非负稀疏编码分别学习图像块多种特征对应的视觉词典,将得到的图像块稀疏向量经过显著性汇总方法引入空间信息并作显著性加权处理,形成整幅图像的稀疏表示,最后采用提出的SDD距离计算方式进行图像检索。在Corel和Caltech通用图像集上进行仿真实验,与单一视觉词典的方法对比,结果表明本文方法能够有效提高图像检索的准确率。In view of application requirements of visual dictionary in image representation and retrieval,this paper proposes an image retrieval method based on the combination of multiple visual dictionaries and saliency weight,which can represent image features with saliency and sparsity.Firstly,the image is divided into blocks,and different kinds of underlying features of image blocks are extracted.Secondly,the image block features are used to learn the multiple visual dictionaries through non-negative sparse coding.The spatial information and saliency are introduced into the sparse vectors for the image blocks by the saliency pooling method,and saliency weight is introduced to form the sparse representation of the entire image.Finally,aproposed SDD distance is used for image retrieval.Compared with the method of single visual dictionary on common image dataset Corel and Caltech,Experimental results demonstrate that the proposed method can effectively improve the image retrieval accuracy.

关 键 词：多视觉词典 非负稀疏编码 显著性加权 相似性度量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]