Volume 17, Issue 4 (2-2021)
JSDP 2021, 17(4): 139-154 |
Back to browse issues page
Department of Computer Engineering, Faculty of Engineering, Yazd University
Abstract: (3366 Views)
Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise changes the output values of a system, just as the value recorded in the output differs from its actual value. In the process of image encoding and transmission, when the image is passed through noisy transmission channel, the impulse noise with positive and negative pulses causes the image to be destroyed. A positive pulse in the form of white and a negative pulse in the form of black affect the image. The purpose of this paper is to introduce dynamic pooling which make the convolutional neural network stronger against the noisy image. The proposed method classifies noise images by weighting the values in the dynamic pooling region. In this research, a new method for modifying the pooling operator is presented in order to increase the accuracy of convolutional neural network in noise image classification. To remove noise in the dynamic pooling layer, it is sufficient to prevent the noise pixel processing by the dynamic pooling operator. Preventing noise pixel processing in the dynamic pooling layer prevents selecting the amount of noise to be applied to subsequent CNN layers. This increases the accuracy of the classification. There is a possibility of destroying the pixels of the entire window in the image. Due to the fact that the dynamic pooling operator is repeated several times in the layers of the convolutional neural network, the proposed method for merging noise pixels can be used many times. In the proposed dynamic pooling layer, pixels with a probability of p being destroyed by noise are not included in the dynamic pooling operation with the same probability. In other words, the participation of a pixel in the dynamic pooling layer depends on the health of that pixel value. If a pixel is likely to be noisy, it will not be processed in the proposed dynamic pooling layer with the same probability. To compare the proposed method, the trained VGG-Net model with medium and slow architecture has been used. Five convolutional layers and three fully connected layers are the components of the proposed model. The proposed method with 26% error for images corrupted with impulse noise with a density of 5% has a better performance than the compared methods. Increased efficiency and speed of convolutional neural network based on dynamic pooling layer modification for noise image classification is seen in the simulation results.
Type of Study: Research |
Subject:
Paper
Received: 2018/12/12 | Accepted: 2020/01/22 | Published: 2021/02/22 | ePublished: 2021/02/22
Received: 2018/12/12 | Accepted: 2020/01/22 | Published: 2021/02/22 | ePublished: 2021/02/22
References
1. [1] Y. Hou, Z. Li, P. Wang, and W. Li, "Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks," IEEE Trans. Circuits Syst. Video Technol., vol. 28, no. 3, pp. 807-811, 2018. [DOI:10.1109/TCSVT.2016.2628339]
2. [2] C. Ding and D. Tao, "Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 1002-1014, 2018. [DOI:10.1109/TPAMI.2017.2700390] [PMID]
3. [3] L. C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs," IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834-848, 2018. [DOI:10.1109/TPAMI.2017.2699184] [PMID]
4. [4] G. Lin, Q. Wu, L. Qiu, and X. Huang, "Image super-resolution using a dilated convolutional neural network," Neurocomputing, vol. 275, pp. 1219-1230, 2018. [DOI:10.1016/j.neucom.2017.09.062]
5. [5] S. Yu, S. Jia, C. X.- Neurocomputing, and undefined 2017, "Convolutional neural networks for hyperspectral image classification," Elsevier, vol. 219, pp. 88-98, 2016. [DOI:10.1016/j.neucom.2016.09.010]
6. [6] J. Yim and K. A. Sohn, "Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets," DICTA 2017 - 2017 Int. Conf. Digit. Image Comput. Tech. Appl., vol. 2017-Decem, pp. 1-8, 2017. [DOI:10.1109/DICTA.2017.8227427]
7. [7] Z. Zhang, D. Han, J. Dezert, and Y. Yang, "A new adaptive switching median filter for impulse noise reduction with pre-detection based on evidential reasoning," Signal Processing, vol. 147, pp. 173-189, 2018. [DOI:10.1016/j.sigpro.2018.01.027]
8. [8] K. H. Jin and J. C. Ye, "Sparse and low-rank decomposition of a hankel structured matrix for impulse noise removal," IEEE Trans. Image Process., vol. 27, no. 3, pp. 1448-1461, 2018. [DOI:10.1109/TIP.2017.2771471] [PMID]
9. [9] I. Turkmen, "The ANN based detector to remove random-valued impulse noise in images," J. Vis. Commun. Image Represent., vol. 34, pp. 28-36, 2016. [DOI:10.1016/j.jvcir.2015.10.011]
10. [10] S. Liang, S. Lu, J. Chang, and C. C. T. Lin, "A Novel Two-Stage Impulse Noise Removal Technique Based on Neural Networks and Fuzzy Decision," Ieeexplore.Ieee.Org, vol. 16, no. 4, pp. 863-873, 2008. [DOI:10.1109/TFUZZ.2008.917297]
11. [11] V. K. Alilou and F. Yaghmaee, "Non-texture image inpainting using histogram of oriented gradients," J. Vis. Commun. Image Represent., vol. 48, pp. 43-53, 2017. [DOI:10.1016/j.jvcir.2017.06.003]
12. [12] A. Javaheri, H. Zayyani, and F. Marvasti, "Sparse recovery of missing image samples using a convex similarity index," Signal Processing, vol. 152, pp. 90-103, 2018. [DOI:10.1016/j.sigpro.2018.05.022]
13. [13] D. Shabtay, N. Raviv, and Y. Moshe, "Video packet loss concealment detection based on image content," Eur. Signal Process. Conf., 2008.
14. [14] G. Nikolakopoulos, P. Stavrou, D. Tsitsipis, D. Kandris, A. Tzes, and T. Theocharis, "A dual scheme for compression and restoration of sequentially transmitted images over Wireless Sensor Networks," Ad Hoc Networks, vol. 11, no. 1, pp. 410-426, 2013. [DOI:10.1016/j.adhoc.2012.07.003]
15. [15] R. G. Everitt and R. H. Glendinning, "A statistical approach to the problem of restoring damaged and contaminated images," Pattern Recognit., vol. 42, no. 1, pp. 115-125, 2009. [DOI:10.1016/j.patcog.2008.06.009]
16. [16] B. Dong, H. Ji, J. Li, Z. Shen, and Y. Xu, "Wavelet frame based blind image inpainting," Appl. Comput. Harmon. Anal., vol. 32, no. 2, pp. 268-279, 2012. [DOI:10.1016/j.acha.2011.06.001]
17. [17] H. Li, W. Luo, and J. Huang, "Localization of Diffusion-Based Inpainting in Digital Images," IEEE Trans. Inf. Forensics Secur., vol. 12, no. 12, pp. 3050-3064, 2017. [DOI:10.1109/TIFS.2017.2730822]
18. [18] C. Qin, C. C. Chang, and K. N. Chen, "Adaptive self-recovery for tampered images based on VQ indexing and inpainting," Signal Processing, vol. 93, no. 4, pp. 933-946, 2013. [DOI:10.1016/j.sigpro.2012.11.013]
19. [19] K. Audhkhasi, O. Osoba, and B. Kosko, "Noise-enhanced convolutional neural networks," Neural Networks, vol. 78, pp. 15-23, 2016. [DOI:10.1016/j.neunet.2015.09.014] [PMID]
20. [20] I. F. Jafar, R. A. Alna'Mneh, and K. A. Darabkh, "Efficient improvements on the BDND filtering algorithm for the removal of high-density impulse noise," IEEE Trans. Image Process., vol. 22, no. 3, pp. 1223-1232, 2013. [DOI:10.1109/TIP.2012.2228496] [PMID]
21. [21] S. Esakkirajan, T. Veerakumar, A. N. Subramanyam, and C. H. PremChand, "Removal of High Density Salt and Pepper Noise Through Modified Decision Based Unsymmetric Trimmed Median Filter," IEEE Signal Process. Lett., vol. 18, no. 5, pp. 287-290, 2011. [DOI:10.1109/LSP.2011.2122333]
22. [22] C. Guillemot and O. Le Meur, "Image Inpainting," IEEE Signal Process. Mag., no. JANUARY, pp. 127-144, 2014. [DOI:10.1109/MSP.2013.2273004]
23. [23] J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, and T. Chen, "Recent advances in convolutional neural networks," Pattern Recognit., vol. 77, pp. 354-377, 2018. [DOI:10.1016/j.patcog.2017.10.013]
24. [24] Y. Liu, Y. M. Zhang, X. Y. Zhang, and C. L. Liu, "Adaptive spatial pooling for image classification," Pattern Recognit., vol. 55, pp. 58-67, 2016. [DOI:10.1016/j.patcog.2016.01.030]
25. [25] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," 2014.
26. [26] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, "ImageNet Large Scale Visual Recognition Challenge," Int. J. Comput. Vis., vol. 115, no. 3, pp. 211-252, 2015. [DOI:10.1007/s11263-015-0816-y]
27. [27] Y. Wang, A. Szlam, and G. Lerman, "Robust Locally Linear Analysis with Applications to Image Denoising and Blind Inpainting," SIAM J. Imaging Sci., vol. 6, no. 1, pp. 526-562, 2013. [DOI:10.1137/110843642]
28. [28] M. Yan, "Restoration of Images Corrupted by Impulse Noise and Mixed Gaussian Impulse Noise using Blind Inpainting," SIAM J. Imaging Sci., vol. 6, no. 3, pp. 1227-1245, 2013. [DOI:10.1137/12087178X]
29. [29] J. Salmon, Z. Harmany, C. A. Deledalle, and R. Willett, "Poisson noise reduction with non-local PCA," J. Math. Imaging Vis., vol. 48, no. 2, pp. 279-294, 2014. [DOI:10.1007/s10851-013-0435-6]
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |