作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (18): 215-216. doi: 10.3969/j.issn.1000-3428.2008.18.077

• 人工智能及识别技术 • 上一篇    下一篇

基于信息瓶颈算法的图像分割

谭立球,夏利民,谷士文   

  1. (中南大学信息工程学院,长沙 410075)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-09-20 发布日期:2008-09-20

Image Segmentation Based on Information Bottleneck Algorithm

TAN Li-qiu, XIA Li-min, GU Shi-wen   

  1. (School of Information Engineering, Central South University, Changsha 410075)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-09-20 Published:2008-09-20

摘要: 图像分割是图像信息处理的内容之一。分割方法有很多,其中较为典型的是模糊C均值(FCM)算法,但它存在一些缺陷。该文提出一种基于信息瓶颈的图像分割方法,用凝聚的信息瓶颈算法对图像像素进行聚类。在分割过程中,使用贝叶斯信息准则确定图像区域的类别数。对一个包含500幅图像的图像库进行实验,结果表明该方法具有很好的分割效果。

关键词: 图像分割, 信息瓶颈, 贝叶斯信息准则

Abstract: Image segmentation is of great importance in the field of image processing. A wide variety of approaches have been proposed for image segmentation. Among them, Fuzzy C-Means (FCM) is a classic one. There are some disadvantages in FCM. A method of image segmentation based on information bottleneck is proposed. This agglomerative information bottleneck method is applied to cluster image pixel. In the process of image segmentation, Bayes Information Criterion(BIC) is used to determine the number of image region class. The system has been implemented and tested on an image database of about 500 images. Experimental results show good segmenting performance of this method.

Key words: image segmentation, information bottleneck, Bayes Information Criterion(BIC)

中图分类号: