计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (18): 177-180.

• 图形、图像、模式识别 • 上一篇    下一篇

基于加权香农熵的图像阈值法

吴成茂1,2   

  1. 1.西安邮电学院 电子与信息工程系,西安 710121
    2.中国科学院 自动化研究所 模式识别国家重点实验室,北京 100080
  • 收稿日期:2007-09-17 修回日期:2007-12-12 出版日期:2008-06-21 发布日期:2008-06-21
  • 通讯作者: 吴成茂

Image thresholding based on weighting shannon entropy

WU Cheng-mao1,2   

  1. 1.Department of Electronics and Information Engineering,Xi’an Institute of Post and Telecommunications,Xi’an 710121,China
    2.National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100080,China
  • Received:2007-09-17 Revised:2007-12-12 Online:2008-06-21 Published:2008-06-21
  • Contact: WU Cheng-mao

摘要: 熵阈值法是图像分割的一种重要方法,在图像处理与识别中广为应用。针对最大熵阈值法是基于图像灰度分布的均匀性假设,导致它对有些图像分割无效的问题,首先提出了加权信息熵的图像分割新方法,其次对加权信息熵的灰度级权因子选取方式进行了探讨,最后给出了基于类内熵和类间熵相结合的图像分割效果评价新方法。实验结果表明,提出的方法是可行的。

Abstract: Entropy based thresholding is an important method of image segmentation and is used in the image processing for many applications.This paper considers that the method of thresholding based on maximal entropy,which requests system interior satisfying uniformity hypothesis of image gray level distribution,is not suitable to segment some images.New method of thresholding based on weighting information entropy is proposed in this paper,and then discuss how to choose weighting factor of weighting information entropy for image segmentation.In the end,the new evaluating method based on intra-class and inter-class entropy is put forward.The experimental results show that the method of this paper is feasible.