基于CNN噪声分离模型的噪声水平估计算法
|
摘要
现有的噪声水平估计(noise level estimation, NLE)算法通常采取先将图像内容信号与噪声信号分离,然后基于分离出的噪声信号估计出图像噪声水平值的实现策略.由于仅有噪声图像本身的信息可以利用,这些算法为保证噪声分离的准确性设计了各种复杂的处理过程,导致其执行效率偏低.为此,提出一种新的基于卷积神经网络噪声分离模型的NLE算法.首先,对大量原始无失真图像施加不同噪声水平的高斯噪声获得噪声图像集合,然后利用卷积神经网络构建一个专门从噪声图像中分离噪声信号获得噪声映射图(noise mapping)的预测模型.考虑到噪声映射图的系数值具有类高斯分布特性,利用广义高斯分布(generalized Gaussian distribution, GGD)模型对噪声映射图建模并以模型参数值作为反映图像噪声水平高低的特征值.最后,利用改进的BP神经网络将该特征值映射为最终的噪声水平预测值.大量实验数据表明:所提出的NLE算法在预测准确度和执行效率2个方面的综合性能优于现有的NLE算法,更具实用价值.
The existing noise level estimation(NLE) algorithms usually adopt the strategy that separates the noise signal from the content of an image to estimate its noise level. Since only a single noisy image can be exploited, these algorithms usually design a variety of complex processes to ensure the accuracy of noise separation, resulting in low execution efficiency. To this end, a novel NLE algorithm using convolutional neural network(CNN)-based noise separation model is proposed in this paper. Specifically, we first add Gaussian noise with different levels to a great amount of representative undistorted images to obtain a training database. Then, we train a CNN-based noise separation model on the training database to obtain the noise mapping from a given noisy image. Considering the fact that the coefficients of the noise mapping show Gaussian distribution behavior, we utilize the generalized Gaussian distribution(GGD) to model the coefficients of the noise mapping, and use two parameters(scale and shape) of the model as the noise level-aware features(NLAF) to describe the level of a noisy image. Finally, an improved back propagation(BP) neural network is used to map the NLAF features to the final noise level. Extensive experiments demonstrate that our method outperforms the most existing classical NLE algorithms in terms of both computational efficiency and estimation accuracy, which makes it more practical to use.
The existing noise level estimation(NLE) algorithms usually adopt the strategy that separates the noise signal from the content of an image to estimate its noise level. Since only a single noisy image can be exploited, these algorithms usually design a variety of complex processes to ensure the accuracy of noise separation, resulting in low execution efficiency. To this end, a novel NLE algorithm using convolutional neural network(CNN)-based noise separation model is proposed in this paper. Specifically, we first add Gaussian noise with different levels to a great amount of representative undistorted images to obtain a training database. Then, we train a CNN-based noise separation model on the training database to obtain the noise mapping from a given noisy image. Considering the fact that the coefficients of the noise mapping show Gaussian distribution behavior, we utilize the generalized Gaussian distribution(GGD) to model the coefficients of the noise mapping, and use two parameters(scale and shape) of the model as the noise level-aware features(NLAF) to describe the level of a noisy image. Finally, an improved back propagation(BP) neural network is used to map the NLAF features to the final noise level. Extensive experiments demonstrate that our method outperforms the most existing classical NLE algorithms in terms of both computational efficiency and estimation accuracy, which makes it more practical to use.
引文
[1]Xu Shaoping,Zeng Xiaoxia,Tang Yiling.Fast noise level estimation algorithm based on two-stage support vector regression[J].Journal of Computer-Aided Design & Computer Graphics,2018,30(3):447- 458 (in Chinese)(徐少平,曾小霞,唐祎玲.基于两阶段支持向量回归的快速噪声水平估计算法[J].计算机辅助设计与图形学学报,2018,30(3):447- 458)
[2]Wang Lingfeng,Huang Zehao,Gong Yongchao,et al.Ensemble based deep networks for image super-resolution[J].Pattern Recognition,2017,68(8):191- 198
[3]Ren Jingjing,Fang Xianyong,Chen Shangwen,et al.Image deblurring based on fast convolutional neural networks[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(8):1444- 1456 (in Chinese)(任静静,方贤勇,陈尚文,等.基于快速卷积神经网络的图像去模糊[J].计算机辅助设计与图形学学报,2017,29(8):1444- 1456)
[4]Dabov K,Foi A,Katkovnik V,et al.Image denoising by sparse 3D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080- 2095
[5]Huang Dongmei,Dai Liang,Wei Lifei,et al.A secure outsourced fusion denoising scheme in multiple encrypted remote sensing images[J].Journal of Computer Research and Development,2017,54(10):2378- 2389 (in Chinese)(黄冬梅,戴亮,魏立斐,等.一种安全的多帧遥感图像的外包融合去噪方案[J].计算机研究与发展,2017,54(10):2378- 2389)
[6]Dong Weisheng,Zhang Lei,Shi Guangming,et al.Nonlocally centralized sparse representation for image restoration[J].IEEE Transactions on Image Processing,2013,22(4):1620- 1630
[7]Immerk?r J.Fast noise variance estimation[J].Computer Vision and Image Understanding,1996,64(2):300- 302
[8]Zoran D,Weiss Y.Scale invariance and noise in natural images[C] //Proc of the 12th IEEE Int Conf on Computer Vision (ICCV 2009).Piscataway,NJ:IEEE,2009:2209- 2216
[9]Katase H,Yamaguchi T,Fujisawa T,et al.Image noise level estimation by searching for smooth patches with discrete cosine transform[C] //Proc of the 59th IEEE Int Midwest Symp on Circuits and Systems.Piscataway,NJ:IEEE,2016.DOI:10.1109/MWSCAS.2016.7870110
[10]Rakhshanfar M,Amer M A.Estimation of Gaussian,Poissonian-Gaussian,and processed visual noise and its level function[J].IEEE Transactions on Image Processing,2016,25(9):4172- 4185
[11]Chen Guangyong,Zhu Fengyuan,Heng P A.An efficient statistical method for image noise level estimation[C] //Proc of the 18th IEEE Int Conf on Computer Vision(ICCV 2015).Piscataway,NJ:IEEE,2015:477- 485
[12]Xu Shaoping,Hu Lingyan,Yang Xiaohui.Quality-aware features-based noise level estimator for block matching and three-dimensional filtering algorithm[J].Journal of Electronic Imaging,2016,25(1):013029
[13]Xu Shaoping,Zeng Xiaoxia,Jiang Yinnan,et al.A multiple image-based noise level estimation algorithm[J].IEEE Signal Processing Letters,2017,24(11):1701- 1705
[14]Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C] //Proc of the 27th IEEE Conf on Computer Vision and Pattern Recognition (CVPR 2014).Piscataway,NJ:IEEE,2014:580- 587
[15]Taigman Y,Yang Ming,Ranzato M,et al.Web-scale training for face identification[C] //Proc of the 18th IEEE Conf on Computer Vision and Pattern Recognition (CVPR 2015).Piscataway,NJ:IEEE,2015:2746- 2754
[16]Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640- 651
[17]Chang Liang,Deng Xiaoming,Zhou Mingquan,et al.Convolutional neural networks in image understanding[J].Acta Automatica Sinica,2016,42(9):1300- 1312 (in Chinese)(常亮,邓小明,周明全,等.图像理解中的卷积神经网络[J].自动化学报,2016,42(9):1300- 1312)
[18]Zhou Feiyan,Jin Linpeng,Dong Jun.Review of convolutional neural network[J].Chinese Journal of Computers,2017,40(6):1229- 1251 (in Chinese)(周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报,2017,40(6):1229- 1251)
[19]Nair V,Hinton G E.Rectified linear units improve restricted Boltzmann machines[C] //Proc of the 27th Int Conf on Int Conf on Machine Learning.New York:ACM,2010:807- 814
[20]Rawat W,Wang Zenghui.Deep convolutional neural networks for image classification:A comprehensive review[J].Neural Computation,2017,29(9):2352- 2449
[21]Li Yanghao,Wang Naiyan,Shi Jianping,et al.Adaptive batch normalization for practical domain adaptation[J].Pattern Recognition,2016,80:109- 117
[22]Mallat S G.A theory for multiresolution signal decomposition:The wavelet representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674- 693
[23]Sun Bo,Chen Songcan,Wang Jiandong,et al.A robust multi-class AdaBoost algorithm for mislabeled noisy data[J].Knowledge-Based Systems,2016,102(5):87- 102
[24]Arbelaez P,Maire M,Fowlkes C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898- 916
[25]Liu Xinhao,Tanaka M,Okutomi M.Single-image noise level estimation for blind denoising[J].IEEE Transactions on Image Processing,2013,22(12):5226- 5237
[2]Wang Lingfeng,Huang Zehao,Gong Yongchao,et al.Ensemble based deep networks for image super-resolution[J].Pattern Recognition,2017,68(8):191- 198
[3]Ren Jingjing,Fang Xianyong,Chen Shangwen,et al.Image deblurring based on fast convolutional neural networks[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(8):1444- 1456 (in Chinese)(任静静,方贤勇,陈尚文,等.基于快速卷积神经网络的图像去模糊[J].计算机辅助设计与图形学学报,2017,29(8):1444- 1456)
[4]Dabov K,Foi A,Katkovnik V,et al.Image denoising by sparse 3D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080- 2095
[5]Huang Dongmei,Dai Liang,Wei Lifei,et al.A secure outsourced fusion denoising scheme in multiple encrypted remote sensing images[J].Journal of Computer Research and Development,2017,54(10):2378- 2389 (in Chinese)(黄冬梅,戴亮,魏立斐,等.一种安全的多帧遥感图像的外包融合去噪方案[J].计算机研究与发展,2017,54(10):2378- 2389)
[6]Dong Weisheng,Zhang Lei,Shi Guangming,et al.Nonlocally centralized sparse representation for image restoration[J].IEEE Transactions on Image Processing,2013,22(4):1620- 1630
[7]Immerk?r J.Fast noise variance estimation[J].Computer Vision and Image Understanding,1996,64(2):300- 302
[8]Zoran D,Weiss Y.Scale invariance and noise in natural images[C] //Proc of the 12th IEEE Int Conf on Computer Vision (ICCV 2009).Piscataway,NJ:IEEE,2009:2209- 2216
[9]Katase H,Yamaguchi T,Fujisawa T,et al.Image noise level estimation by searching for smooth patches with discrete cosine transform[C] //Proc of the 59th IEEE Int Midwest Symp on Circuits and Systems.Piscataway,NJ:IEEE,2016.DOI:10.1109/MWSCAS.2016.7870110
[10]Rakhshanfar M,Amer M A.Estimation of Gaussian,Poissonian-Gaussian,and processed visual noise and its level function[J].IEEE Transactions on Image Processing,2016,25(9):4172- 4185
[11]Chen Guangyong,Zhu Fengyuan,Heng P A.An efficient statistical method for image noise level estimation[C] //Proc of the 18th IEEE Int Conf on Computer Vision(ICCV 2015).Piscataway,NJ:IEEE,2015:477- 485
[12]Xu Shaoping,Hu Lingyan,Yang Xiaohui.Quality-aware features-based noise level estimator for block matching and three-dimensional filtering algorithm[J].Journal of Electronic Imaging,2016,25(1):013029
[13]Xu Shaoping,Zeng Xiaoxia,Jiang Yinnan,et al.A multiple image-based noise level estimation algorithm[J].IEEE Signal Processing Letters,2017,24(11):1701- 1705
[14]Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C] //Proc of the 27th IEEE Conf on Computer Vision and Pattern Recognition (CVPR 2014).Piscataway,NJ:IEEE,2014:580- 587
[15]Taigman Y,Yang Ming,Ranzato M,et al.Web-scale training for face identification[C] //Proc of the 18th IEEE Conf on Computer Vision and Pattern Recognition (CVPR 2015).Piscataway,NJ:IEEE,2015:2746- 2754
[16]Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640- 651
[17]Chang Liang,Deng Xiaoming,Zhou Mingquan,et al.Convolutional neural networks in image understanding[J].Acta Automatica Sinica,2016,42(9):1300- 1312 (in Chinese)(常亮,邓小明,周明全,等.图像理解中的卷积神经网络[J].自动化学报,2016,42(9):1300- 1312)
[18]Zhou Feiyan,Jin Linpeng,Dong Jun.Review of convolutional neural network[J].Chinese Journal of Computers,2017,40(6):1229- 1251 (in Chinese)(周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报,2017,40(6):1229- 1251)
[19]Nair V,Hinton G E.Rectified linear units improve restricted Boltzmann machines[C] //Proc of the 27th Int Conf on Int Conf on Machine Learning.New York:ACM,2010:807- 814
[20]Rawat W,Wang Zenghui.Deep convolutional neural networks for image classification:A comprehensive review[J].Neural Computation,2017,29(9):2352- 2449
[21]Li Yanghao,Wang Naiyan,Shi Jianping,et al.Adaptive batch normalization for practical domain adaptation[J].Pattern Recognition,2016,80:109- 117
[22]Mallat S G.A theory for multiresolution signal decomposition:The wavelet representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674- 693
[23]Sun Bo,Chen Songcan,Wang Jiandong,et al.A robust multi-class AdaBoost algorithm for mislabeled noisy data[J].Knowledge-Based Systems,2016,102(5):87- 102
[24]Arbelaez P,Maire M,Fowlkes C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898- 916
[25]Liu Xinhao,Tanaka M,Okutomi M.Single-image noise level estimation for blind denoising[J].IEEE Transactions on Image Processing,2013,22(12):5226- 5237