浏览全部资源
扫码关注微信
Received：16 September 2019，
Revised：2019-12-14，
Accepted：21 December 2019，
Published：16 July 2020
移动端阅览
目的
2
利用深度卷积神经网络（deep convolutional neural network，DCNN）构建的非开关型随机脉冲噪声（random-valued impulse noise，RVIN）降噪模型在降噪效果和执行效率上均比主流的开关型RVIN降噪算法更有优势，但在实际应用中，这类基于训练（数据驱动）的降噪模型，其性能却受制于能否对待降噪图像受噪声干扰的严重程度进行准确的测定（即存在数据依赖问题）。为此，提出了一种基于浅层卷积神经网络的快速RVIN噪声比例预测（noise ratio estimation，NRE）模型。
方法
2
该预测模型的主要任务是检测待降噪图像中的噪声比例值并将其作为反映图像受噪声干扰严重程度的指标，依据NRE预测模型的检测结果可以自适应调用相应预先训练好的特定区间DCNN降噪模型，从而快速且高质量地完成图像降噪任务。
结果
2
分别在10幅常用图像和50幅纹理图像两个测试集上进行测试，并与现有的主流RVIN降噪算法中的检测模块进行对比。在常用图像测试集上，本文所提出的NRE预测模型的预测准确性最高。相比于噪声比例预测精度排名第2的算法，NRE预测模型在噪声比例预测值均方根误差上低0.6% 2.4%。在50幅纹理图像测试集上，NRE模型的均方根误差波动范围最小，表明其稳定性最好。通过在1幅大小为512×512像素图像上的总体平均执行时间来比较各个算法执行效率的优劣，NRE模型执行时间仅为0.02 s。实验数据表明：所提出的NRE预测模型在受各种不同噪声比例干扰的自然图像上均可以快速而稳定地测定图像中受RVIN噪声干扰的严重程度，非盲的DCNN降噪模型与其联用后即可无缝地转化为盲降噪算法。
结论
2
本文RVIN噪声比例预测模型在各个噪声比例下具有鲁棒的预测准确性，与基于DCNN的非开关型RVIN深度降噪模型配合使用后能妥善解决DCNN网络模型固有的数据依赖问题。
Objective
2
Nonswitching random-valued impulse noise (RVIN) denoisers built with deep convolution neural networks (DCNNs) have many advantages compared with the mainstream switching RVIN removal algorithms in terms of denoising effect and execution efficiency. However
the performance of training-based (data-driven) denoisers in practical applications experiences inaccurate measurement of the distortion level of a given image to be denoised (data dependency problem). A fast noise ratio estimation (NRE) model based on shallow CNN (SCNN) was proposed in this study.
Method
2
The noise ratio reflecting the distortion level of a given noisy image was estimated using the proposed NRE model. On the basis of the estimated noise ratio
the corresponding DCNN-based denoiser trained at a specific interval of noise ratios can be adaptively exploited to efficiently remove RVIN with high denoised image quality.
Result
2
Comparison experiments were conducted to test the validity of the proposed NRE model from three aspects
namely
estimation accuracy
denoising effect
and execution efficiency. We utilized the NRE model to estimate the noise ratios of given noisy images and compared the results with the existing classical RVIN noise reduction algorithms (including PSMF(progressive switching median filter)
ROLD-EPR(rank-ordered logarithmic difference edge-preserving regularization)
ASWM(adaptive switching median)
ROR-NLM(robust outlyingness ratio nonlocal means)
MLP-EPR(multilayer perceptron edge-preserving regularization)) to verify its estimation accuracy. Considering that these competing algorithms detect noisy pixels in a pixelwise manner
the number of pixels identified as noise was divided by the total number of pixels in the entire image
and the detection results were transformed as noise ratio to facilitate comparison with the proposed NRE model. Two image sets were used
where the first image set included Lena
House
Peppers
Couple
Hill
Barbara
Boat
Man
Cameraman
and Monarch images
and the second image set was randomly selected from the Business Structure Database. For a fair comparison
all the competing algorithms were implemented on MATLAB 2017b and conducted on the same hardware platform. First
noise ratio detection was performed on the first image set
and Lena
Boat
and House images corrupted with different noise ratios were selected for demonstration. Regarding the estimation accuracy of noise ratio
PSMF
ROLD-EPR
and MLP-EPR algorithms are low. The estimation accuracy of the ASWM algorithm is high at high noise ratios
and the prediction accuracy of the ROR-NLM algorithm is high at medium and low noise ratios. The performance of the proposed NRE model consistently ranks in top two. The root mean square error (RMSE) between the estimation results and the ground-truth noise ratios was used to verify the stability of the proposed NRE model. On the first image set
the NRE model outperforms the second-best algorithm by 0.6%-2.4% in terms of RMSE. In the second image set
the RMSE of the proposed NRE model on 50 images is the smallest
indicating that its stability is the best. Although the estimation accuracies of several switching RVIN removal algorithms are higher than the proposed NRE prediction model in some cases
their execution time is extremely long. We applied different ratios of RVIN noise (10%
20%
30%
40%
50% and 60%) to Lena image with size of 512×512 pixels to test the denoising effect and used the pretrained NRE model to estimate the noise ratios for the noisy images. A DnCNN-S(DnCNN for specific ratio range) noise reduction model was used to remove the noise in accordance with the estimation results. Experimental results show that the denoising results with the estimated noise ratios are similar to the ground truth values
indicating that the estimation accuracy of the proposed NRE model is satisfactory. As the preprocessing module of denoising algorithms
the execution efficiency of noise detector is used as an evaluation index that determines the execution performance of the entire denoising algorithm. Only the MLP-EPR algorithm and the NRE+DnCNN-S denoising algorithm proposed in this paper can be clearly divided into two stages
namely
noise detection and noise reduction. Therefore
we provided the execution time of the noise detection module for MLP-EPR and NRE+DnCNN-S algorithms in addition to the average execution time. Regarding the execution time of the noise detection module
the MLP-EPR algorithm needs 0.07 s
whereas the proposed NRE model only needs 0.02 s
indicating that the efficiency of the NRE model is relatively high. Experimental results show that the proposed SCNN-based NRE model can quickly and stably measure the distortion level of a given noisy image corrupted by RVIN under different noise ratios. Any nonblind DCNN-based denoiser combined with the proposed NRE model can be seamlessly converted into a blind version.
Conclusion
2
Extensive experiments show that the estimation accuracy of the proposed CNN-based NRE model is robust under a wide range of noise ratios. DCNN's inherent data dependence problem can be properly solved when the proposed NRE model is combined with DCNN-based non-switching RVIN deep denoising models.
Akkoul S, Ledee R, Leconge R and Harba R. 2010. A new adaptive switching median filter. IEEE Signal Processing Letters, 17(6):587-590[DOI:10.1109/LSP.2010.2048646]
Arbeláez P, Maire M, Fowlkes C and Malik J. 2011. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5):898-916[DOI:10.1109/TPAMI.2010.161]
Chang L, Deng X M, Zhou M Q, Wu Z K, Yuan Y, Yang S and Wang H A. 2016. Convolutional neural networks in image understanding. Acta Automatica Sinica, 42(9):1300-1312
常亮, 邓小明, 周明全, 武仲科, 袁野, 杨硕, 王宏安. 2016.图像理解中的卷积神经网络.自动化学报, 42(9):1300-1312)[DOI:10.16383/j.aas.2016.c150800]
Chen T and Wu H R. 2001. Adaptive impulse detection using center-weighted median filters. IEEE Signal Processing Letters, 8(1):1-3[DOI:10.1109/97.889633]
Dong Y Q, Chan R H and Xu S F. 2007. A detection statistic for random-valued impulse noise. IEEE Transactions on Image Processing, 16(4):1112-1120[DOI:10.1109/TIP.2006.891348]
Garnett R, Huegerich T, Chui C and He W J. 2005. A universal noise removal algorithm with an impulse detector. IEEE Transactions on Image Processing, 14(11):1747-1754[DOI:10.1109/TIP.2005.857261]
Guo S, Yan Z F, Zhang K, Zuo W M and Zhang L. 2019. Toward convolutional blind denoising of real photographs//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE: 1713-1722[ DOI: 10.1109/CVPR.2019.00181 http://dx.doi.org/10.1109/CVPR.2019.00181 ]
Ioffe S and Szegedy C. 2019. Batch normalization: accelerating deep network training by reducing internal covariate shift[EB/OL].[2019-07-15] . https://arxiv.org/pdf/1502.03167.pdf https://arxiv.org/pdf/1502.03167.pdf
Jin K H and Ye J C. 2018. Sparse and low-rank decomposition of a Hankel structured matrix for impulse noise removal. IEEE Transactions on Image Processing, 27(3):1448-1461[DOI:10.1109/TIP.2017.2771471]
Lefkimmiatis S. 2018. Universal denoising networks: a novel CNN architecture for image denoising//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE: 3204-3213[ DOI: 10.1109/CVPR.2018.00338 http://dx.doi.org/10.1109/CVPR.2018.00338 ]
Liu L C, Chen C L P, Zhou Y C and You X G. 2015. A new weighted mean filter with a two-phase detector for removing impulse noise. Information Sciences, 315:1-16[DOI:10.1016/j.ins.2015.03.067]
Rawat W and Wang Z H. 2017. Deep convolutional neural networks for image classification:a comprehensive review. Neural Computation, 29(9):2352-2449[DOI:10.1162/NECO_a_00990]
Shi Y G, Hao H Y and Liu Z W. 2018. Cascaded convolutional neural network based hippocampus subfields segmentation. Journal of Image and Graphics, 23(1):74-83
时永刚, 郝华胤, 刘志文. 2018.串行处理卷积神经网络的海马子区分割.中国图象图形学报, 23(1):74-83)[DOI:10.11834/jig.170334]
Simonyan K and Zisserman A. 2019. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-07-15] . https://arxiv.org/pdf/1409.1556.pdf https://arxiv.org/pdf/1409.1556.pdf
Turkmen I. 2016. The ANN based detector to remove random-valued impulse noise in images. Journal of Visual Communication and Image Representation, 34:28-36[DOI:10.1016/j.jvcir.2015.10.011]
Wang Z and Zhang D. 1999. Progressive switching median filter for the removal of impulse noise from highly corrupted images. IEEE Transactions on Circuits and Systems Ⅱ:Analog and Digital Signal Processing, 46(1):78-80[DOI:10.1109/82.749102]
Xiong B and Yin Z P. 2012. A universal denoising framework with a new impulse detector and nonlocal means. IEEE Transactions on Image Processing, 21(4):1663-1675[DOI:10.1109/TIP.2011.2172804]
Xu Q, Li Y H, Guo Y J, Wu S and Sbert M. 2018. Random-valued impulse noise removal using adaptive ranked-ordered impulse detector. Journal of Electronic Imaging, 27(1):#013001[DOI:10.1117/1.JEI.27.1.013001]
Zhang K, Zuo W M, Chen Y J, Meng D Y and Zhang L. 2017. Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing, 26(7):3142-3155[DOI:10.1109/TIP.2017.2662206]
Zhang K, Zuo W M and Zhang L. 2018. FFDNet:toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing, 27(9):4608-4622[DOI:10.1109/TIP.2018.2839891]
Zhang M H, Zhang F Q, Liu Q G and Wang S S. 2019. VST-Net:variance-stabilizing transformation inspired network for Poisson denoising. Journal of Visual Communication and Image Representation, 62:12-22[DOI:10.1016/j.jvcir.2019.04.011]
Zhou J F, Ye S R and Wang H. 2019. Text sentiment classification based on deep convolutional neural network model. Computer Engineering, 45(3):300-308
周锦峰, 叶施仁, 王晖. 2019.基于深度卷积神经网络模型的文本情感分类.计算机工程, 45(3):300-308)[DOI:10.19678/j.issn.1000-3428.0050043]
相关作者
相关机构
京公网安备11010802024621
