山东科学 ›› 2020, Vol. 33 ›› Issue (4): 124-130.doi: 10.3976/j.issn.1002-4026.2020.04.016

• 其他研究论文 • 上一篇    下一篇

基于Perona-Malik模型改进的图像去噪方法

殷素雅,唐泉*,张新东   

  1. 新疆师范大学数学科学学院,新疆 乌鲁木齐 830017
  • 收稿日期:2020-01-06 出版日期:2020-07-27 发布日期:2020-07-28
  • 通信作者: 唐泉(1991—),男,硕士,研究方向为偏微分方程及其应用研究。
  • 作者简介:殷素雅(1997—),女,硕士研究生,研究方向为偏微分方程数字图像处理。E-mail:1070231198@qq.com
  • 基金资助:
    新疆维吾尔自治区自然科学基金面上科学基金(2018D01A27);国家自然科学基金(11861068);新疆师范大学“十三五”校级重点学科(20SDKD110)

Improved image denoising method based on Perona-Malik model

YIN Su-ya, TANG Quan*, ZHANG Xin   

  1. School of Mathematical Sciences, Xinjiang Normal University, Urumqi 830017,China
  • Received:2020-01-06 Online:2020-07-27 Published:2020-07-28

摘要: 结合冲击滤波器和Perona-Malik(P-M)模型提出一种新的图像去噪模型,在增强图像细节的同时,能够抑制噪声的放大和过冲现象,同时给出的扩散函数可以使模型达到更好的图像去噪效果。仿真结果表明,使用本文模型进行去噪处理后得到的图像在视觉效果和客观评价标准方面均优于P-M模型、CLMC模型以及传统的模型,在去除噪声的同时,能够更好地保留图像的细节和边缘特征。

关键词: 图像去噪, Perona-Malik模型, 冲击滤波器, 图像边缘增强, 扩散函数

Abstract: A new image denoising model based on impulse filter and Perona-Malik(P-M) model is proposed in this study. The denoising model proposed herein can not only enhance the image details but also restrain the noise amplification and overshoot. Simultaneously, the diffusion function obtained in this study can help the model achieve better image denoising effect. Through a large number of simulation experiments, results show that the image obtained by denoising with the proposed model is superior to those obtained by the P-M model, CLMC model and traditional model in terms of both visual effect and objective evaluation. The proposed model can better preserve the details and edge features of the image while removing the noise.

Key words: image denoising, Perona-Malik model, impulse filter, image edge enhancement, diffusion function

中图分类号: 

  • TP391