广义全变分与巴特沃斯高通滤波融合图像去噪

计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (19): 20-22.

广义全变分与巴特沃斯高通滤波融合图像去噪

乔闹生1，2，张奋3

1.湖南文理学院物理与电子科学学院，湖南常德 415000
2.中南大学信息科学与工程学院，长沙 410083
3.湖南文理学院计算机科学与技术学院，湖南常德 415000

出版日期:2014-10-01 发布日期:2014-09-29

Image denoising method based on fusion of generalized total variation and Butterworth high pass filter

QIAO Naosheng1，2, ZHANG Fen3

1.School of Physics and Electronics, Hunan University of Arts and Science, Changde, Hunan 415000, China
2.School of Information Science and Engineering, Central South University, Changsha 410083, China
3.School of Computer Science and Technology, Hunan University of Arts and Science, Changde, Hunan 415000, China

Online:2014-10-01 Published:2014-09-29

摘要/Abstract

摘要： 为了得到既可保留图像低频信息又可增强图像高频信息的去噪后的图像，提出了一种广义全变分范数与巴特沃斯高通滤波器融合的图像去噪方法。分析了广义全变分范数的图像去噪模型基本原理，给出了其优点与缺点；讨论了改进的巴特沃斯高通滤波器图像去噪方法，指出了其优点及不足之处；结合两者的优点，将两种去噪方法进行融合而得到了一种可增强对比度和保留边缘细节的图像去噪方法。计算机仿真的主观与客观实验结果证明了基本原理分析的正确性。

关键词: 图像去噪, 广义全变分范数, 巴特沃斯高通滤波器, 峰值信噪比

Abstract: In order to obtain the image after being denoised that can not only reserve the low frequency information of image but also enhance the high frequency information of image, an image denoising method based on the fusion of generalized total variation model and improved Butterworth high pass filter is proposed. Firstly, the basic principle of the generalized total variation model image denoising is analyzed, and its advantage and disadvantage are given. Secondly, the image denoising method of the improved butterworth high pass filte is discussed, and its advantage and disadvantage are also given. Finally, the two advantages are inosculated and an image denoising method that can not only enhance image contrast but also reserve image edge detail is obtained. Both the subjective result and the objective result of the computer simulation indicate the correctness of the basic principle analysis.

Key words: image denoising, generalized total variation model, Butterworth high pass filter, Peak Signal to Noise Ratio（PSNR）

乔闹生1，2，张奋3. 广义全变分与巴特沃斯高通滤波融合图像去噪[J]. 计算机工程与应用, 2014, 50(19): 20-22.

QIAO Naosheng1，2, ZHANG Fen3. Image denoising method based on fusion of generalized total variation and Butterworth high pass filter[J]. Computer Engineering and Applications, 2014, 50(19): 20-22.

[1]	刘迪，贾金露，赵玉卿，钱育蓉. 基于深度学习的图像去噪方法研究综述[J]. 计算机工程与应用, 2021, 57(7): 1-13.
[2]	陈人和，赖振意，钱育蓉. 改进的生成对抗网络图像去噪算法[J]. 计算机工程与应用, 2021, 57(5): 168-172.
[3]	王洁，金正猛，冯灿. 自适应广义全变差的图像泊松去噪算法[J]. 计算机工程与应用, 2021, 57(20): 203-209.
[4]	呼亚萍，孔韦韦，李萌，黄翠玲. 改进TV图像去噪模型的全景图像拼接算法[J]. 计算机工程与应用, 2021, 57(17): 203-209.
[5]	刘成士，赵志刚，李强，吕慧显，董晓晨，李金霞. 加强的低秩表示图像去噪算法[J]. 计算机工程与应用, 2020, 56(2): 216-225.
[6]	袁小军，周涛，李琛. 基于稀疏先验的非局域聚类图像去噪算法研究[J]. 计算机工程与应用, 2020, 56(18): 177-185.
[7]	杨永鹏，杨真真，李建林，乐俊. 低秩稀疏分解及其在视频和图像处理中的应用[J]. 计算机工程与应用, 2020, 56(16): 21-30.
[8]	钱满，张向阳，李仁昌. 改进卷积神经网络SAR图像去噪算法[J]. 计算机工程与应用, 2020, 56(14): 176-182.
[9]	杨赵琪璘，彭定涛，唐琦，罗孝敏. 基于稀疏优化lp正则化的光滑化拟牛顿算法[J]. 计算机工程与应用, 2019, 55(22): 163-171.
[10]	李敏，章国豪，曾建伟，杨晓锋，胡晓敏. 结合Inception模型的卷积神经网络图像去噪方法[J]. 计算机工程与应用, 2019, 55(20): 139-144.
[11]	张龙，刘朝霞，刘洪琛. 一种去除椒盐噪声带L1保真项的混合变分模型[J]. 计算机工程与应用, 2019, 55(1): 210-216.
[12]	马红强，马时平，许悦雷，吕超，辛鹏，朱明明. 基于改进栈式稀疏去噪自编码器的图像去噪[J]. 计算机工程与应用, 2018, 54(4): 199-204.
[13]	肖佳，张俊华，梅礼晔. 基于改进BM3D算法的椒盐噪声去噪[J]. 计算机工程与应用, 2018, 54(21): 170-175.
[14]	崔金鸽1，陈炳权1，2，徐庆1. 基于Dual-Tree CWT和自适应双边滤波器的图像去噪算法[J]. 计算机工程与应用, 2018, 54(18): 223-228.
[15]	黄亚飞，王国富，张法全，叶金才. 基于蜂群算法和带参阈值函数的图像去噪方法[J]. 计算机工程与应用, 2018, 54(17): 164-168.