计算机工程与应用 ›› 2013, Vol. 49 ›› Issue (21): 156-159.

• 图形图像处理 • 上一篇    下一篇

基于决策融合的图像自动标注方法

欧阳宁1,2,罗晓燕1,莫建文1,2,张  彤3   

  1. 1.桂林电子科技大学 信息与通信学院,广西 桂林 541004
    2.桂林电子科技大学 图像信息研究所,广西 桂林 541004
    3.桂林电子科技大学 机电工程学院,广西 桂林 541004
  • 出版日期:2013-11-01 发布日期:2013-10-30

Method of automatic image annotation based on decision fusion

OUYANG Ning1,2, LUO Xiaoyan1, MO Jianwen1,2, ZHANG Tong3   

  1. 1.School of Information & Communication, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China
    2.Institute of Image Information, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China
    3.School of  Mechatronic Engineering, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China
  • Online:2013-11-01 Published:2013-10-30

摘要: 结合多媒体描述接口(MPEG-7)和MM(Mixture Model)混合模型,实现了基于决策融合的图像自动标注。在图像标注过程中,分别利用颜色描述子和纹理描述子为每个主题下的图像建立MM混合模型,实现低层视觉特征到高层语义空间的映射,利用局部决策融合方式融合在颜色和纹理MM混合模型下的标注结果,实现图像自动标注。通过在corel图像数据集上的实验,表明提出的局部决策融合方式能更充分利用图像的颜色和纹理信息,提高了图像标注性能。

关键词: 图像自动标注, MPEG-7描述子, 混合模型, 决策融合

Abstract: A method for automatic image annotation based on decision fusion is proposed combining the Multimedia Description Interface(MPEG-7) and MM(Mixture Model). In the process of image annotation, two independent MM mixture models are estimated for the images belonging to a theme and mapping is setted up from low-level features to high-level semantics space. Automatic image annotation is achieved by fusing the annotation results from color and text MM mixture model in the way of local decision fusion. The way of local decision fusion is proven to utilize fully the color feature and texture feature and improve the performance of image annotation by the experiments on the image data sets.

Key words: automatic image annotation, MPEG-7 descriptor, Mixture Model(MM), decision fusion