基于主题融合和关联规则挖掘的图像标注  

Image Annotation Based on Topic Fusion and Frequent Patterns Mining

作　　者：张蕾 蔡明[1] ZHANG Lei;CAI Ming(College of Internet of Things Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China)

机构地区：[1]江南大学物联网工程学院

出　　处：《计算机科学》2019年第7期246-251,共6页Computer Science

摘　　要：为减小“语义鸿沟”,在LDA主题模型的基础上,提出了一种主题融合和关联规则挖掘的图像标注方法。首先,针对视觉和文本信息的关联度不高的问题,引入基于向量机的多类别分类得到图像的类别信息。其次,通过文本模态的语义主题分布和类别信息,计算出图像类的文本主题分布。未知图像将其所属类的文本主题分布与其视觉主题分布进行加权融合,并以此概率模型计算初始标签集。最后依据初始标注词概率,利用关联规则挖掘和词间相关性挖掘文本关联度,从而得到精确化语义标注。在Corel5K图像数据集上进行对比实验,实验结果证明了方法的有效性。In order to reduce the“semantic gap”,based on the LDA topic model,an image annotation approach which uses topics fusion and association rule mining was proposed.First,to solve the problem of low correlation between visual and text information,the vector machine-based multi-category classification is introduced to obtain the category information of the image.Then,the text topic distribution of the image class is calculated by the semantic topic distribution and classification information of the text modality.The unknown image weights the text topic distribution of its class and its visual topic distribution,and calculates the initial label set using this probability model.Finally,based on the probability of initial label words,the association rules mining and inter-word correlation are used to mine the text relevance to obtain precise semantic annotation.The comparative experiments were carried out on the Corel5K image dataset.The experimental results show the effectiveness of the proposed method.

关 键 词：图像标注 LDA主题模型 加权主题融合 关联规则挖掘 词间相关性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]