基于视觉语义主题的图像自动标注

Image Automatic Annotation Based on Visual Semantic Topics

为减小图像检索中语义鸿沟的影响,提出了一种基于视觉语义主题的图像自动标注方法。首先,提取图像前景与背景区域,并分别进行预处理;然后,基于概率潜在语义分析与高斯混合模型建立图像底层特征、视觉语义主题与标注关键词间的联系,并基于该模型实现对图像的自动标注。采用corel 5数据库进行验证,实验结果证明了本文方法的有效性。

A novel automatic annotation scheme based on the visual semantic topics is proposed to reduce the impact of semantic gap. Firstly, the foreground and background regions of the image are extracted and pro- cessed respectively. Then, the relations among the low-level feature, the visual semantic topics and the key words are built based on the probabilistic latent semantic analysis（PLSA） and the Gauss mixture model （ GMM）. Finally, the images can be annotated based on the introduced model. The widely used database corel 5 is used as test bed, and the test results validate the new scheme.