基于主成分分析与深度神经网络的快速噪声水平估计算法

doi:10.3969/j.issn.0372-2112.2019.02.003

电子学报 ›› 2019, Vol. 47 ›› Issue (2): 274-281.DOI: 10.3969/j.issn.0372-2112.2019.02.003

基于主成分分析与深度神经网络的快速噪声水平估计算法

徐少平, 李崇禧, 林官喜, 唐祎玲, 胡凌燕

南昌大学信息工程学院, 江西南昌 330031

收稿日期:2018-01-04 修回日期:2018-07-17 出版日期:2019-02-25
- 通讯作者:
- 胡凌燕
- 作者简介:
- 徐少平 男,1976年生于江西九江.博士,南昌大学信息工程学院计算机科学与技术系教授,博士生导师.主要研究方向为图形图像处理、机器视觉、虚拟手术仿真等.E-mail:xushaoping@ncu.edu.cn;李崇禧 男,1994年生于江西吉安.现为南昌大学硕士研究生,主要研究方向为图像处理与计算机视觉;林官喜 女,1992年生于江西吉安.2018年获南昌大学硕士学位,主要研究方向为图像处理与计算机视觉;唐祎玲 女,1977年生于浙江奉化.现为南昌大学博士研究生,主要研究方向为图像处理与计算机视觉.
- 基金资助:
- 国家自然科学基金 (No.61662044，No.61163023，No.81501560，No.51765042）; 江西省自然科学基金 (No.20171BAB202017）

Fast Image Noise Level Estimation Algorithm Based on Principal Component Analysis and Deep Neural Network

XU Shao-ping, LI Chong-xi, LIN Guan-xi, TANG Yi-ling, HU Ling-yan

School of Information Engineering, Nanchang University, Nanchang, Jiangxi 330031, China

Received:2018-01-04 Revised:2018-07-17 Online:2019-02-25 Published:2019-02-25
- Supported by:
- National Natural Science Foundation of China (No.61662044, No.61163023, No.81501560, No.51765042); Natural Science Foundation of Jiangxi Province, China (No.20171BAB202017)

摘要/Abstract

摘要： 鉴于从噪声图像分解获得的原生图块集合的协方差矩阵前若干个特征值（按照升序排序）与图像噪声水平值具有强相关性，提出了一种基于主成分分析和深度神经网络的快速噪声水平估计算法.该算法首先选用原生图块集合协方差矩阵前若干个特征值构成刻画图像噪声水平高低的特征矢量，然后在大量有代表性且已标定噪声水平值的噪声图像集合上利用深度神经网络训练预测模型以实现将特征矢量直接映射为噪声水平值，最后为获得更高的预测准确性，采用粗精预测模型相结合的两步预测方式实现.实验表明：文中算法在各个噪声级别上都具有稳定的预测准确性，且执行效率非常高，作为降噪算法的前置预处理模块具有更好的综合优势.

关键词: 图像降噪, 噪声水平估计, 主成分分析, 深度神经网络, 粗精结合策略

Abstract: Considering the fact that there exists the strong correlation between the first several eigenvalues (in ascending order)of the covariance matrix of the raw patches extracted from a noisy image and its noise level,we proposed a novel fast multiple image-based noise level estimation (FMNLE)algorithm using the principal component analysis (PCA)and the deep neural network (DNN).Specifically,we selected the first several eigenvalues of the raw patches to form a feature vector characterizing the noise level of an image.Then,we employed deep neural network to train an estimation model on a large number of representative natural images corrupted with known noise levels,by which the feature vector can be directly mapped into the corresponding noise level.To obtain higher estimation accuracy,a two-step estimation strategy was adopted.Extensive experiments show that,the estimation accuracy of the proposed algorithm is stable at each noise level with good efficiency,demonstrating a better comprehensive advantage as the pre-processing module for denoising algorithms.

Key words: image denoising, noise level estimation, principal component analysis, deep neural network, coarse-to-fine strategy

中图分类号:

TP391

徐少平, 李崇禧, 林官喜, 等. 基于主成分分析与深度神经网络的快速噪声水平估计算法[J]. 电子学报, 2019, 47(2): 274-281.

XU Shao-ping, LI Chong-xi, LIN Guan-xi, et al. Fast Image Noise Level Estimation Algorithm Based on Principal Component Analysis and Deep Neural Network[J]. Acta Electronica Sinica, 2019, 47(2): 274-281.

参考文献

[1] Xu S P,Zeng X X,Jiang Y N,et al.A multiple image-based noise level estimation algorithm[J].IEEE Signal Processing Letters,2017,24(11):1701-1705.
[2] 徐少平,张兴强,姜尹楠,等.局部均值噪声估计的盲3维滤波降噪算法[J].中国图象图形学报,2017,22(4):422-434. Xu Shao-ping,Zhang Xing-qiang,Jiang Yin-nan,et al.Noise level estimation based on local means and its application to the blind BM3D denoising algorithm[J].Journal of Image and Graphics,2017,22(4):422-434.(in Chinese)
[3] 周先春,吴婷,石兰芳,等.一种基于曲率变分正则化的小波变换图像去噪方法[J].电子学报,2018,46(3):621-628. Zhou Xian-chun,Wu Ting,Shi Lan-fang,et al.A kind of wavelet transform image denoising method based on curvature variation regularization[J].Acta Electronica Sinica,2018,46(3):621-628.(in Chinese)
[4] Dabov K,Foi A,Katkovnik V,et al.Image denoising with block-matching and 3D filtering[A].SPIE 6064,Image Processing:Algorithms and Systems,Neural Networks,and Machine Learning[C].San Jose,CA,United States,2006,354-365.
[5] 杨学志,叶铭,周芳,等.采用混合特征相似性的极化SAR图像降噪算法[J].电子学报,2016,44(11):2583-2591. Yang Xue-zhi,Ye Ming,Zhou Fang,et al.Speckle reduction for polSAR images using hybrid features similarity[J].Acta Electronica Sinica,2016,44(11):2583-2591.(in Chinese)
[6] Ghazi M M,Erdogan H.Image noise level estimation based on higher-order statistics[J].Multimedia Tools and Applications,2017,76(2):2379-2397.
[7] Xu S P,Hu L Y,Yang X H.Quality-aware features-based noise level estimator for block matching and three-dimensional filtering algorithm[J].Journal of Electronic Imaging,2016,25(1):Article No.013029.
[8] Donoho D L,Johnstone I M.Adapting to unknown smoothness via wavelet shrinkage[J].Journal of the American Statistical Association,1995,90(432):1200-1224.
[9] Immerkaer J.Fast noise variance estimation[J].Computer Vision and Image Understanding,1996,64(2):300-302.
[10] 张旗,梁德群,樊鑫.基于小波域的图像噪声估计新方法[J].计算机工程,2004,30(8):37-39. Zhang Qi,Liang De-qun,Fan Xin.Estimating image noise based on region segmentation in the wavelet domain[J].Computer Engineering,2004,30(8):37-39.(in Chinese)
[11] Zoran D,Weiss Y.Scale invariance and noise in natural images[A].2009 IEEE 12th International Conference on Computer Vision[C].Kyoto,Japan:IEEE,2009,2209-2216.
[12] Liu W,Lin W S.Additive white Gaussian noise level estimation in SVD domain for images[J].IEEE Transactions on Image Processing,2013,22(3):872-833.
[13] Pyatykh S,Hesser J,Zheng L.Image noise level estimation by principal component analysis[J].IEEE Transactions on Image Processing,2013,22(2):687-699.
[14] Liu X H,Tanaka M,Okutomi M.Single-image noise level estimation for blind denoising[J].IEEE Transactions on Image Processing,2013,22(12):5226-5237.
[15] Cui G M,Feng H J,Xu Z H,et al.No-reference image noise estimation based on noise level accumulation[J].Optical Review,2016,23(2):208-219.
[16] Zhang L,Zhang L,Bovik A C.A feature-enriched completely blind image quality evaluator[J].IEEE Transactions on Image Processing,2015,24(8):2579-2591.
[17] Hinton G,Deng L,Dong Y,et al.Deep neural networks for acoustic modeling in speech recognition:the shared views of four research groups[J].IEEE Signal Processing Magazine,2012,29(6):82-97.
[18] Tanaka M,Okutomi M.A novel inference of a restricted Boltzmann machine[A].201422nd International Conference on Pattern Recognition[C].Stockholm,Sweden:IEEE,2014,1526-1531.
[19] Abdullah S M,Tischer P,Wijewickrema S,et al.Hierarchical mutual nearest neighbour image segmentation[A].2016 International Conference on Digital Image Computing:Techniques & Applications (DICTA)[C].Gold Coast,QLD,Australia:IEEE,2016,1-8.
[20] Chen G Y,Zhu F Y,Heng P A.An efficient statistical method for image noise level estimation[A].2015 IEEE International Conference on Computer Vision[C].Santiago,Chile:IEEE,2015,477-485.
[21] Yang S M,Tai S C.Fast and reliable image-noise estimation using a hybrid approach[J].Journal of Electronic Imaging,2010,19(3):033007.
[22] Zhang K,Zuo W M,Chen Y J,et al.Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising[J].IEEE Transactions on Image Processing,2017,26(7):3142-3155.

基于主成分分析与深度神经网络的快速噪声水平估计算法

Fast Image Noise Level Estimation Algorithm Based on Principal Component Analysis and Deep Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王硕, 王坚, 王亚男, 宋亚飞. 一种基于特征融合的恶意代码快速检测方法[J]. 电子学报, 2023, 51(1): 57-66.
[2]	周奕涛, 张斌, 刘自豪. 基于多模态深度神经网络的应用层DDoS攻击检测模型[J]. 电子学报, 2022, 50(2): 508-512.
[3]	陈星宇, 叶锋, 黄添强, 翁彬, 陈家祯, 林文忠. 融合小型深度生成模型的显著性检测[J]. 电子学报, 2021, 49(4): 768-774.
[4]	肜娅峰, 陈晨, 陈德运, 何勇军. 基于贝叶斯主成分分析的i-vector说话人确认方法[J]. 电子学报, 2021, 49(11): 2186-2194.
[5]	黎毅达, 高发荣, 姚婷, 蔡利杰. 基于Fisher判别和GKF-RELM算法的多特征步态模式识别[J]. 电子学报, 2021, 49(10): 1993-2001.
[6]	崔子豪, 鲍长春. 基于广义合成分析和深度神经网络的自回归系数估计方法[J]. 电子学报, 2021, 49(1): 29-39.
[7]	刘金平, 王杰, 唐朝晖, 贺俊宾, 谢永芳, 马天雨. 基于自适应滑窗递归稀疏主成分分析的工业过程故障监测[J]. 电子学报, 2020, 48(9): 1795-1803.
[8]	袁文浩, 胡少东, 时云龙, 李钊, 梁春燕. 一种用于语音增强的卷积门控循环网络[J]. 电子学报, 2020, 48(7): 1276-1283.
[9]	蒋留兵, 周小龙, 车俐. 基于无载波超宽带雷达的小样本人体动作识别[J]. 电子学报, 2020, 48(3): 602-615.
[10]	张嘉纹, 党小宇, 杨凌辉, 齐茹梦, 王萌. 海面短波地波通信中基于DNN神经网络的单样本极化滤波器预测研究[J]. 电子学报, 2020, 48(11): 2250-2257.
[11]	袁文浩, 娄迎曦, 梁春燕, 夏斌. 利用生成噪声提高语音增强方法的泛化能力[J]. 电子学报, 2019, 47(4): 791-797.
[12]	胡钢, 徐翔, 张维明, 周鋆. 基于主成分分析的网络节点重要性指标贡献评价[J]. 电子学报, 2019, 47(2): 358-365.
[13]	陈楠, 鲍长春. 基于双耳线索编码原理的语音增强方法[J]. 电子学报, 2019, 47(1): 227-233.
[14]	田文飚, 芮国胜, 董道广, 康健. 基于盲自适应KLT的蒸发波导压缩感知方法[J]. 电子学报, 2018, 46(9): 2068-2074.
[15]	代晓婷, 龚敬, 聂生东. 基于结构联合字典的肺部LDCT图像降噪[J]. 电子学报, 2018, 46(6): 1445-1453.