计算机应用 ›› 2010, Vol. 30 ›› Issue (12): 3295-3297.

• 虚拟现实与模式识别 • 上一篇    下一篇

基于多模态关联图的图像语义标注方法

郭玉堂1,罗斌2   

  1. 1. 合肥师范学院
    2.
  • 收稿日期:2010-05-20 修回日期:2010-08-08 发布日期:2010-12-22 出版日期:2010-12-01
  • 通讯作者: 郭玉堂
  • 基金资助:
    基于内容的视频信息结构化建模方法研究;基于图理论的图像语义自动标注研究

Image semantic annotation method based on multi-modal relational graph

  • Received:2010-05-20 Revised:2010-08-08 Online:2010-12-22 Published:2010-12-01
  • Contact: Guo YuTang

摘要: 为了改善图像标注的性能,提出了一种基于多模态关联图的图像语义标注方法。该方法用一个无向图表达了图像区域特征、标注词以及图像三者之间的关系,结合图像区域特征相似性和语义间的相关性提取图像语义信息,提高了图像标注的精度。利用逆向文档频率(IDF)修正图像节点与其标注词节点之间边的权值,克服了传统方法中因高频词引起的偏差,有效地提高了图像标注的性能。在Corel图像数据集上进行了实验,实验结果验证了该方法的有效性。

关键词: 图像语义, 多模态图, 逆向文档频率, 高频词

Abstract: In order to improve the performance of the image annotation, an image semantic annotation method based on multi-modal relational graph was proposed. The relationship between the low-level features of the image region, annotated words and images was presented by an undirected graph. Semantic information was extracted by combining similarity measured in the region feature space and the correlation of annotation words to improve the accuracy of the extracted semantics. Inverse Document Frequency (IDF) was introduced to adjust the weights of edges between the image node and its annotation words node in order to overcome the deviation caused by high-frequency words. It can effectively improve the image annotation performance. The experimental results on the Corel image datasets show the effectiveness of the proposed approach in terms of quality of the image annotation.

Key words: image semantic, multi-modal graph, Inverse Document Frequency (IDF), high-frequency word