Semantic image annotation based on GMM and random walk model  

作　　者：田东平 

机构地区：[1]Institute of Computer Software, Baoji University of Arts and Sciences, Baoji 721007, P. R. China [2]Institute of Computational Information Science, Baoji University of Arts and Sciences, Baoji 721007, P. R. China

出　　处：《High Technology Letters》2017年第2期221-228,共8页高技术通讯（英文版）

基　　金：Supported by the National Basic Research Program of China(No.2013CB329502);the National Natural Science Foundation of China(No.61202212);the Special Research Project of the Educational Department of Shaanxi Province of China(No.15JK1038);the Key Research Project of Baoji University of Arts and Sciences(No.ZK16047)

摘　　要：Automatic image annotation has been an active topic of research in computer vision and pattern recognition for decades.A two stage automatic image annotation method based on Gaussian mixture model(GMM) and random walk model(abbreviated as GMM-RW) is presented.To start with,GMM fitted by the rival penalized expectation maximization(RPEM) algorithm is employed to estimate the posterior probabilities of each annotation keyword.Subsequently,a random walk process over the constructed label similarity graph is implemented to further mine the potential correlations of the candidate annotations so as to capture the refining results,which plays a crucial role in semantic based image retrieval.The contributions exhibited in this work are multifold.First,GMM is exploited to capture the initial semantic annotations,especially the RPEM algorithm is utilized to train the model that can determine the number of components in GMM automatically.Second,a label similarity graph is constructed by a weighted linear combination of label similarity and visual similarity of images associated with the corresponding labels,which is able to avoid the phenomena of polysemy and synonym efficiently during the image annotation process.Third,the random walk is implemented over the constructed label graph to further refine the candidate set of annotations generated by GMM.Conducted experiments on the standard Corel5 k demonstrate that GMM-RW is significantly more effective than several state-of-the-arts regarding their effectiveness and efficiency in the task of automatic image annotation.Automatic image annotation has been an active topic of research in computer vision and pattern recognition for decades.A two stage automatic image annotation method based on Gaussian mixture model（GMM） and random walk model（abbreviated as GMM-RW） is presented.To start with,GMM fitted by the rival penalized expectation maximization（RPEM） algorithm is employed to estimate the posterior probabilities of each annotation keyword.Subsequently,a random walk process over the constructed label similarity graph is implemented to further mine the potential correlations of the candidate annotations so as to capture the refining results,which plays a crucial role in semantic based image retrieval.The contributions exhibited in this work are multifold.First,GMM is exploited to capture the initial semantic annotations,especially the RPEM algorithm is utilized to train the model that can determine the number of components in GMM automatically.Second,a label similarity graph is constructed by a weighted linear combination of label similarity and visual similarity of images associated with the corresponding labels,which is able to avoid the phenomena of polysemy and synonym efficiently during the image annotation process.Third,the random walk is implemented over the constructed label graph to further refine the candidate set of annotations generated by GMM.Conducted experiments on the standard Corel5 k demonstrate that GMM-RW is significantly more effective than several state-of-the-arts regarding their effectiveness and efficiency in the task of automatic image annotation.

关 键 词：semantic image annotation Gaussian mixture model （ GMM） random walk rival penalized expectation maximization （RPEM） image retrieval 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]