吉林大学学报(信息科学版) ›› 2019, Vol. 37 ›› Issue (6): 603-609.

• • 上一篇    下一篇

基于2D-VMD 与CC 结合的模态重构算法

高宏宇1a,1b,马立园1a,1b,董宏丽1a,1b,路敬祎1a,1b,刘文庆2   

  1. 1. 东北石油大学a. 电气信息工程学院; b. 黑龙江省网络化与智能控制重点实验室,黑龙江大庆163318;2. 西部钻探井下作业公司C12343 队,新疆克拉玛依834000
  • 出版日期:2019-11-24 发布日期:2020-01-03
  • 作者简介:高宏宇( 1979— ) ,女,黑龙江大庆人,东北石油大学副教授,硕士生导师,主要从事智能控制与复杂网络系统滤波研究,( Tel) 86-13936997593( E-mail) 4501419@ qq. com; 董宏丽( 1977— ) ,女,黑龙江克山人,东北石油大学教授,博士生导师,主要从事智能控制和网络化控制研究,( Tel) 86-459-6503373( E-mail) shiningdhl@ vip. 126. com。
  • 基金资助:
    黑龙江省自然科学重点基金资助项目( ZD2019F001) ; 东北石油大学青年科学基金资助项目(2018QNL-30)

Reconstruction Algorithm Based on 2D-VMD and CC

GAO Hongyu1a,1 b,MA Liyuan1a,1 b,DONG Hongli1a,1 b,LU Jingyi1a,1b,LIU Wenqing2   

  1. 1a. School of Electrical Engineering and Information; 1b. Heilongjiang Provincial Key Laboratory of Networking and
    Intelligent Control,Northeast Petroleum University,Daqing 163318,China;2. C12343 Team,Downhole Service Company of Xibu Drilling Engineering Company Limited,Karamay 834000,China
  • Online:2019-11-24 Published:2020-01-03

摘要: 为提高重构图像的质量,针对二维变分模态分解( 2D-VMD: Two Dimensional Variational Mode Decomposition) 算法需确定分解尺度K 值和有效固有模态分量的问题,提出了将2D-VMD 结合相关系数( CC: Correlation Coefficient) 的联合算法,并用于图像重构。该方法首先利用2D-VMD 将图像信号分解为不同中心频率的子模态,然后计算分解后的固有模态函数( IMF: Intrinsic Mode Function) 与原始图像函数的CC 值,根据CC 准则确定有效的固有模态分量,最后利用有效的固有模态分量进行重构,实现了图像去噪。仿真结果表明,2D-VMD 和CC 结合可以准确得到分解尺度K 和有效的子模态,具有很高的图像重构精度,提高了图像质量。

关键词: 二维变分模态分解, 相关系数, 图像去噪, 模态重构

Abstract: To improve the quality of reconstructed images,it is necessary to determine the decomposition scale K value and the effective intrinsic mode function in 2D-VMD ( Two Dimensional Variational Mode Decomposition) algorithm,a new algorithm combined 2D-VMD and CC ( Correlation Coefficient) is proposed and used to reconstruct image. Firstly,the image signal is decomposed into sub-modes of different central frequencies by 2D-VMD. Then,the CC value of the decomposed Intrinsic Mode Function ( IMF) and the original image function is calculated to determine the effective Intrinsic Mode component according to the CC criterion.Finally,image denoising is achieved by reconstruct with effective intrinsic modal component. Simulation results show that the decomposition scale K and the effective sub-modes can be obtained through combined 2D-VMD and CC,which has high image reconstruction accuracy and improved image quality.

Key words: two dimensional variational mode decomposition, correlation coefficient, image denoising, modal reconstruction

中图分类号: 

  • TN911. 73