Noise Removal from the Image Using Convolutional Neural Networks-Based Denoising Auto Encoder

Abstract

With the exponential growth in the volume of digital images captured daily, there is an escalating demand for elevating image quality to achieve both accuracy and visual appeal. Addressing this need, the development of techniques for reducing image noise while preserving crucial features, such as edges, corners, and sharp structures, has become imperative. This paper delves into the significance of image denoising and introduces a novel approach utilizing a denoising autoencoder based on convolutional neural networks (CNNs). The proposed method adopts a meticulous two-step process to effectively eliminate noise. Initially, input images are segregated into training and testing sets. Subsequently, a denoising autoencoder model is trained using the designated training data. This model is then further refined through training on a CNN, enhancing its noise reduction capabilities. The evaluation of the system's performance is conducted using testing data to gauge its effectiveness. The study employs the MATLAB programming language for implementation and evaluation. Results, measured through RMSE (Root Mean Square Error) and PSNR (Peak Signal-to-Noise Ratio) criteria on two distinct datasets—the Covid19-radiography-database and SIIM-medical-images—reveal that our proposed method outperforms existing approaches significantly. This approach is particularly promising for applications demanding enhanced image quality, such as the resolution enhancement of medical images. The study contributes to the ongoing efforts in noise reduction research, offering a robust solution for improving visual perception in diverse image processing applications.

Keywords

• image noise
• denoising autoencoder
• convolutional neural network
• image denoising

References

1. A. A. Saraiva, M. S. de Oliveira, P. B. de Moura Oliveira, E. J. Solteiro Pires, N. M. Fonseca Ferreira, and A. Valente, “Genetic algorithm applied to remove noise in DICOM images,” J. Inf. Optim. Sci., vol. 40, no. 7, pp. 1543–1558, 2019, doi: 10.1080/02522667.2019.1597999.
2. S. Rani, Y. Chabrra, and K. Malik, “An Improved Denoising Algorithm for Removing Noise in Color Images,” Eng. Technol. Appl. Sci. Res., vol. 12, no. 3, pp. 8738–8744, 2022, doi: 10.48084/etasr.4952.
3. D. G. Kim, M. Hussain, M. Adnan, M. A. Farooq, Z. H. Shamsi, and A. Mushtaq, “Mixed Noise Removal Using Adaptive Median Based Non-Local Rank Minimization,” IEEE Access, vol. 9, pp. 6438–6452, 2021, doi: 10.1109/ACCESS.2020.3048181.
4. A. Mukherjee, S. Sarkar, and S. K. Saha, “Segmentation of natural images based on super pixel and graph merging,” IET Comput. Vis., vol. 15, no. 1, pp. 1–11, 2021, doi: 10.1049/cvi2.12008.
5. A. Jindal, N. Aggarwal, and S. Gupta, “An Obstacle Detection Method for Visually Impaired Persons by Ground Plane Removal Using Speeded-Up Robust Features and Gray Level Co-Occurrence Matrix,” Pattern Recognit. Image Anal., vol. 28, no. 2, pp. 288–300, 2018, doi: 10.1134/S1054661818020086.
6. R. Chauhan, K. K. Ghanshala, and R. C. Joshi, “Convolutional Neural Network (CNN) for Image Detection and Recognition,” ICSCCC 2018 - 1st Int. Conf. Secur. Cyber Comput. Commun., pp. 278–282, 2018, doi: 10.1109/ICSCCC.2018.8703316.
7. Y. Zhang, “A Better Autoencoder for Image: Convolutional Autoencoder,” pp. 1–7, 2015.
8. A. Semwal, A. Chamoli, and A. Semwal, “A SURVEY : On Image Denoising And Its Various Techniques,” Int. Res. J. Eng. Technol., pp. 1565–1568, 2017.

9. K. Zhang, W. Zuo, and L. Zhang, “FFDNet: Toward a fast and flexible solution for CNN-Based image denoising,” IEEE Trans. Image Process., vol. 27, no. 9, pp. 4608–4622, 2018, doi: 10.1109/TIP.2018.2839891.
10. A. E. Ilesanmi and T. O. Ilesanmi, “Methods for image denoising using convolutional neural network: a review,” Complex Intell. Syst., vol. 7, no. 5, pp. 2179–2198, 2021, doi: 10.1007/s40747-021-00428-4.
11. B. Goyal, A. Dogra, S. Agrawal, B. S. Sohi, and A. Sharma, “Image denoising review: From classical to state-of-the-art approaches,” Inf. Fusion, vol. 55, pp. 220–244, 2020, doi: 10.1016/j.inffus.2019.09.003.
12. S. Sudha, G. R. Suresh, and R. Sukanesh, “Speckle Noise Reduction in Satellite Images Using Spatially Adaptive Wavelet Thresholding,” Int. J. Comput. Sci. Inf. Technol., vol. 3, no. 2, pp. 3432–3435, 2012.
13. A. A. A. Goshtasby, “Advances in Computer Vision and Pattern Recognition,” Image Regist. Princ. Tools methods, pp. 7–66, 2012, [Online]. Available: http://www.springerlink.com/index/10.1007/978-1-4471-2458-0
14. K. Bajaj, D. K. Singh, and M. A. Ansari, “Autoencoders Based Deep Learner for Image Denoising,” Procedia Comput. Sci., vol. 171, pp. 1535–1541, 2020, doi: 10.1016/j.procs.2020.04.164.
15. P. Svoboda, M. Hradis, D. Barina, and P. Zemcik, “Compression artifacts removal using convolutional neural networks,” J. WSCG, vol. 24, no. 2, pp. 63–72, 2016.
16. P. Vincent, H. Larochelle, Y. Bengio, and P. A. Manzagol, “Extracting and composing robust features with denoising autoencoders,” Proc. 25th Int. Conf. Mach. Learn., pp. 1096–1103, 2008, doi: 10.1145/1390156.1390294.
17. F. Agostinelli, M. R. Anderson, and H. Lee, “Adaptive multi-column deep neural networks with application to robust image denoising,” Adv. Neural Inf. Process. Syst., 2013.
18. L. Gondara, “Medical Image Denoising Using Convolutional Denoising Autoencoders,” IEEE Int. Conf. Data Min. Work. ICDMW, vol. 0, pp. 241–246, 2016, doi: 10.1109/ICDMW.2016.0041.
19. B. Du et al., “Stacked Convolutional Denoising Auto-Encoders for Feature Representation,” IEEE Trans. Cybern., vol. 47, no. 4, pp. 1017–1027, 2017.
20. S. S. Roy, S. I. Hossain, M. A. H. Akhand, and K. Murase, “A robust system for noisy image classification combining denoising autoencoder and convolutional neural network,” Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 1, pp. 224–235, 2018, doi: 10.14569/IJACSA.2018.090131.
21. J. Lehtinen et al., “Noise2Noise: Learning image restoration without clean data,” 35th Int. Conf. Mach. Learn. ICML 2018, vol. 7, pp. 4620–4631, 2018.
22. A. Krull, T. O. Buchholz, and F. Jug, “Noise2void-Learning denoising from single noisy images,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2019-June, pp. 2124–2132, 2019, doi: 10.1109/CVPR.2019.00223.
23. J. Batson and L. Royer, “Noise2Seif: Blind denoising by self-supervision,” 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 826–835, 2019.
24. Y. Fang and T. Zeng, “Learning deep edge prior for image denoising,” Comput. Vis. Image Underst., vol. 200, 2020, doi: 10.1016/j.cviu.2020.103044.
25. X. Fu, S. Jia, L. Zhuang, M. Xu, J. Zhou, and Q. Li, “Hyperspectral Anomaly Detection via Deep Plug-and-Play Denoising CNN Regularization,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 11, pp. 9553–9568, 2021, doi: 10.1109/TGRS.2021.3049224.
26. T. Wu, W. Li, S. Jia, Y. Dong, and T. Zeng, “Deep multi-level wavelet-CNN denoiser prior for restoring blurred image with cauchy noise,” IEEE Signal Process. Lett., vol. 27, pp. 1635–1639, 2020, doi: 10.1109/LSP.2020.3023299.
27. B. Ahn and N. I. Cho, “Block-Matching Convolutional Neural Network for Image Denoising,” 2017, [Online]. Available: http://arxiv.org/abs/1704.00524
28. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” IEEE Trans. Image Process., vol. 26, no. 7, pp. 3142–3155, 2017, doi: 10.1109/TIP.2017.2662206.
29. B. Guo, K. Song, H. Dong, Y. Yan, Z. Tu, and L. Zhu, “NERNet: Noise estimation and removal network for image denoising,” J. Vis. Commun. Image Represent., vol. 71, 2020, doi: 10.1016/j.jvcir.2020.102851.
30. S. Gai and Z. Bao, “New image denoising algorithm via improved deep convolutional neural network with perceptive loss,” Expert Syst. Appl., vol. 138, 2019, doi: 10.1016/j.eswa.2019.07.032.
31. L. Zhang, Y. Li, P. Wang, W. Wei, S. Xu, and Y. Zhang, “A separation–aggregation network for image denoising,” Appl. Soft Comput. J., vol. 83, 2019, doi: 10.1016/j.asoc.2019.105603.
32. X. Li et al., “Detail retaining convolutional neural network for image denoising,” J. Vis. Commun. Image Represent., vol. 71, 2020, doi: 10.1016/j.jvcir.2020.102774.
33. D. Yin et al., “Speckle noise reduction in coherent imaging based on deep learning without clean data,” Opt. Lasers Eng., vol. 133, 2020, doi: 10.1016/j.optlaseng.2020.106151.
34. L. Jin, W. Zhang, G. Ma, and E. Song, “Learning deep CNNs for impulse noise removal in images,” J. Vis. Commun. Image Represent., vol. 62, pp. 193–205, 2019, doi: 10.1016/j.jvcir.2019.05.005.
35. “https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database.”
36. “https://www.kaggle.com/datasets/kmader/siim-medical-images”.
37. R. Butuner, & M. H. Calp. Diagnosis and Detection of COVID-19 from Lung Tomography Images Using Deep Learning and Machine Learning Methods. International Journal of Intelligent Systems and Applications in Engineering, 10(2), 190-200, 2022.
38. B. Guler Ayyildiz, R. Karakis, B. Terzioglu, & D. Ozdemir. Comparison of deep learning methods for the radiographic detection of patients with different periodontitis stages. Dentomaxillofacial Radiology, 53(1), 32-42, 2024.
39. Q. Gazawy, S. Buyrukoglu and A. Akbas, "Deep Learning for Enhanced Education Quality: Assessing Student Engagement and Emotional States," 2023 Innovations in Intelligent Systems and Applications Conference (ASYU), Sivas, Türkiye, 2023, pp. 1-8, doi: 10.1109/ASYU58738.2023.10296748.
40. O. Güler, & İ. Yücedağ, Artırılmış Gerçeklik: Montaj ve Bakım Uygulamalarında El Tanıma Teknolojisi İle Etkileşim Çalışmaları. Paper presented at the 20. Akademik Bilişim Konferansı, Karabük. 2018. http://indexive.com/uploads/papers/pap_indexive15949797202147483647.pdf
41. N. Daldal, Z. A. Sezer, M. Nour, A. Alhudhaif, K. Polat, A New Generation Communication System Based on Deep Learning Methods for the Process of Modulation and Demodulation from the Modulated Images, Mathematical Problems in Engineering, vol. 2022, Article ID 9555598, 13 pages, 2022. https://doi.org/10.1155/2022/9555598.
42. R. Bütüner and M. H. Calp, (2023). Robotic Systems and Artificial Intelligence Applications in Agriculture. Current Studies in Technology, Innovation and Entrepreneurship, 145.