Novel Measures Based on Simple Schur Concave Function for Image Registration

YANG Jing; HU Shun-bo; LIU Chang-chun; YANG Jin-bao

您当前的位置：

首页 >

文章列表页 >

Novel Measures Based on Simple Schur Concave Function for Image Registration

更新时间：2025-07-16

- Novel Measures Based on Simple Schur Concave Function for Image Registration
- Acta Electronica Sinica Vol. 36, Issue 12, Pages: 2328-2332(2008)
- 作者机构：
  
  1. 山东大学计算机科学与技术学院,山东,济南,250101
  2. 山东大学控制科学与工程学院,山东,济南,250061
  3. 临沂师范学院物理系,山东,临沂,276005
  4. 山东大学计算机科学与技术学院山东济南,250101
  5. 山东大学控制科学与工程学院山东济南,250061
  6. 临沂师范学院物理系山东临沂,276005
- 作者简介：
- 基金信息：
- DOI：
  CLC： R318
- Published：2008
- 稿件说明：
移动端阅览
YANG Jing, HU Shun-bo, LIU Chang-chun, et al. Novel Measures Based on Simple Schur Concave Function for Image Registration[J]. Acta Electronica Sinica, 2008, 36(12): 2328-2332.
DOI：

YANG Jing, HU Shun-bo, LIU Chang-chun, et al. Novel Measures Based on Simple Schur Concave Function for Image Registration[J]. Acta Electronica Sinica, 2008, 36(12): 2328-2332. DOI：

摘要

使用互信息或归一化互信息进行图像配准时

由于噪声、模态、插值等影响

测度函数存在许多局部极值

收敛范围较窄

有可能导致误配准.该文根据一个简单的Schur凹函数

充分利用它的特殊上凸性来消除噪声等引起的小概率分布

并由Jensen-Schur测度、广义距离测度和 f 信息测度的定义

构造了六种新测度.从运算时间、收敛性能、抗噪鲁棒性方面

对这六种测度、互信息和归一化互信息进行了比较和分析.实验结果表明

Jensen-Schur-beta和D-beta测度的收敛性能优于其它测度

抗噪声能力强于其它测度

运算速度快于互信息和归一化互信息.

Abstract

When the influence of noise

interpolation and image modality is considered

the image registration method based on mutual information or normalized mutual information may cause local extrema

small convergence area

and even inaccurate registration.According to a simple Schur concave function and the definition of Jensen-Schur measure

generalized divergence measure and f information measure

six new measures were constructed.The Schur function with special concave characteristics can filter the small probability distribution caused by noise

interpolation and so on.The characters of six new measures

mutual information and normalized mutual information are analyzed and compared by applying them to rigid registration.The results of tests show that Jensen-Schur-beta and D-beta measures outperform other measures in convergence performance and noise immunity

and they are time saving in comparison with mutual information and normalized mutual information measures.

关键词

Keywords

references

Views

1284

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Registration Method for Blur Deformation Image Based on Orthogonal Legendre Moment

Fusion Algorithm for Incomplete Fingerprint Orientation Field Reconstruction Based on Gradient Dispersion and Mutual Information

Genetic Sequential IB Algorithm

Related Author

ZUO Xin

DAI Xiu-bin

ZHANG Hui

LUO Li-min

SHU Hua-zhong

ZHANG Bo

JING Xiao-jun

SUN Song-lin

Related Institution

School of Geography and Biological InformationNanjing University of Posts and TelecommunicationsNanjingJiangsu 210003China

School of Computer Science and EngineeringJiangsu University of Science and TechnologyZhenjiangJiangsu 212003China

Lab of Image Science and TechnologySchool of Computer Science and EngineeringSoutheast UniversityNanjingJiangsu 210096China

School of Geography and Biological Information, Nanjing University of Posts and Telecommunications

School of Computer Science and Engineering, Jiangsu University of Science and Technology

⁰