计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (32): 188-191.DOI: 10.3778/j.issn.1002-8331.2010.32.053

• 图形、图像、模式识别 • 上一篇    下一篇

低层特征获取高层语义的图像检索

梁竞敏   

  1. 广东女子职业技术学院 艺术设计与信息技术系,广州 511450
  • 收稿日期:2009-03-31 修回日期:2009-06-23 出版日期:2010-11-11 发布日期:2010-11-11
  • 通讯作者: 梁竞敏

Image retrieval method of getting high-level semantics from low-level features

LIANG Jing-min   

  1. Department of Arts Design and Information Technology,Guangdong Women’s Polytechnic College,Guangzhou 511450,China
  • Received:2009-03-31 Revised:2009-06-23 Online:2010-11-11 Published:2010-11-11
  • Contact: LIANG Jing-min

摘要: 首先采用基于颜色聚类的方法将图像分割成区域,提取每个区域的Gabor小波纹理特征和灰度共生矩阵纹理特征,接着采用信息熵对特征进行选择,使用选择后的特征对图像区域进行聚类,得到每幅图像的语义特征向量;然后提出遗传模糊C均值算法对图像进行聚类。在图像检索时,查询图像和聚类中心比较,在距离最小的类中进行检索。实验表明,提出的方法可以明显提高检索效率,提高了检索的精度。

Abstract: A method based on color cluster is used to divide images into regions,and the Gabor wavelet features and gray-level co-occurrence matrix texture features of each region are extracted,and information entropy is used to select feature and reduce the feature dimensionality,then using these features to cluster image region and the semantic feature is gained;then using genetic fuzzy C-means clustering algorithm to cluster image.In image retrieval,the querying image is compared to cluster center,then retrieved in the class with the minimal distance.The experiment results show that the proposed approach has an excellent retrieval precision.

中图分类号: