Regularization Otsu’s Thresholding Method Based on Posterior Probability Entropy

WU Cheng-mao

doi:10.3969/j.issn.0372-2112.2013.12.024

您当前的位置：

首页 >

文章列表页 >

Regularization Otsu’s Thresholding Method Based on Posterior Probability Entropy

更新时间：2025-07-16

- Regularization Otsu’s Thresholding Method Based on Posterior Probability Entropy
- Acta Electronica Sinica Vol. 41, Issue 12, Pages: 2474-2478(2013)
- 作者机构：
  
  1. 西安邮电大学电子工程学院,陕西,西安,710121
  2. 西安邮电大学电子工程学院,陕西,西安,710121
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61073106);Program of Education Department of Shaanxi Province (No.2010JK816);Weapon Equipment Pre- Research Foundation of China (No.9140A25030411HK339)
- DOI：10.3969/j.issn.0372-2112.2013.12.024
  CLC： TP391
- Published：2013
- 稿件说明：
移动端阅览
WU Cheng-mao. Regularization Otsu’s Thresholding Method Based on Posterior Probability Entropy[J]. Acta Electronica Sinica, 2013, 41(12): 2474-2478.
DOI：

WU Cheng-mao. Regularization Otsu’s Thresholding Method Based on Posterior Probability Entropy[J]. Acta Electronica Sinica, 2013, 41(12): 2474-2478. DOI： 10.3969/j.issn.0372-2112.2013.12.024.

摘要

Otsu阈值法是一种广泛应用的图像分割方法，但它并不适合目标和背景类内方差相差较大的图像分割需要，于是本文提出了一种基于分割所得目标和背景后验概率信息熵约束的正则化Otsu分割改进方法.从图像分割本质是像素聚类问题的观点出发，首先将传统Otsu阈值法解释为一种加权硬C-均值聚类；其次考虑到聚类问题具有典型的不适定性，利用图像分割所得目标和背景的后验概率所对应信息熵作为约束项，实现Otsu阈值化准则函数的正则化修改并得到了正则化Otsu阈值分割法；最后对该分割方法的合理性进行解释并给出其正则参数选取方法.实验结果表明，本文所建议的正则化Otsu阈值法是有效的，并将传统Otsu阈值法视为特例.

Abstract

Otsu's thresholding method is widely applied in image segmentation

but it is not suitable to segment the images that have large difference in intra-class variance of object and background

this paper presents a regularization Otsu's segmentation method based on the information entropy of posterior probability of object and background obtained by thresholding image.From the point of view that image segmentation is essentially pixel clustering problem

the classical Otsu's thresholding method is firstly interpreted as a kind of weighting hard C-means clustering algorithm.Secondly

considering that the clustering segmentation has typical ill-posedness

the object and background from raw image are obtained by segmentation and their posterior probability information entropy is taken as the constraint item

the regularized modification of Otsu's thresholding criteria function is realized

and regularization Otsu's thresholding method is obtained.In the end

the reasonability of the proposed thresholding method is explained by mathematical analysis

and the selection method of its regularization parameter is put forward.Experimental results show that the proposed regularization Otsu's thresholding method is effective

and the traditional Ostu's thresholding method can be viewed as a special case of the proposed method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Precise Two-Dimensional Otsu's Image Segmentation and Its Fast Recursive Realization

An Image Segmentation Fuzzy Method Based on Multi-Dictionary Learning

Enhanced PFCM Algorithm for Noisy Image Segmentation Combining Regional and Neighborhood-Level Information

SwinT-Unet: Ultrasound Image Segmentation Based on Two-Channel Self-Attention Mechanism

A Variational Level Set Model Based on Beer-Lambert Law

Related Author

ZHANG Xin-ming

SUN Yin-jie

ZHENG Yan-bin

LI Ya-feng

WANG Xiao-peng

WANG Hai-zhou

CHEN Hao-ran

SONG Yan-tao

Related Institution

College of Computer and Information Technology, Henan Normal University

School of Computer Science and Technology, Baoji University of Arts and Science.

School of Computer Science and Technology Baoji University of Arts and Science. Baoji Shaanxi China

School of Electronic and Information Engineering, Lanzhou Jiaotong University

Institute of Big Data Science & Industry, Shanxi University

⁰