Muazzez Buket DARICI, Zeki ERDEM

A Comparative Study on Denoising from Facial Images Using Convolutional Autoencoder

Denoising is one of the most important preprocesses in image processing. Noises in images can prevent extracting some important information stored in images. Therefore, before some implementations such as image classification, segmentation, etc., image denoising is a necessity to obtain good results. The purpose of this study is to compare the deep learning techniques and traditional techniques on denoising facial images considering two different types of noise (Gaussian and Salt&Pepper). Gaussian, Median, and Mean filters have been specified as traditional methods. For deep learning methods, deep convolutional denoising autoencoders (CDAE) structured on three different optimizers have been proposed. Both accuracy metrics and computational times have been considered to evaluate the denoising performance of proposed autoencoders, and traditional methods. The utilized standard evaluation metrics are the peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM). It has been observed that overall, while the traditional methods gave results in shorter times in terms of computation times, the autoencoders performed better concerning the evaluation metrics. The CDAE based on the Adam optimizer has been shown the best results in terms of PSNR and SSIM metrics on removing both types of noise.

Keywords:

Denoising, Autoencoder Salt&pepper noise, Gaussian noise,

PDF

___

[1] Fan, L., Zhang, F., Fan, H. and Zhang, C., “Brief review of image denoising techniques,” Visual Computing for Industry, Biomedicine, and Art, 7, (2019).
[2] Alisha P. B. and G. S. K., “Image Denoising Techniques-An Overview,” 11: 78–84, (2016).
[3] Patidar, P., Gupta, M., Srivastava, S. and Nagawat, A. K., “Image De-noising by Various Filters for Different Noise,” International Journal of Computer Applications, 9: 45–50, (2010).
[4] Tun, N. M., Gavrilov, A. I. and Tun, N. L., “Facial image denoising using convolutional autoencoder network,” Proceedings - 2020 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2020, 1–5, (2020).
[5] Bajaj, K., Singh, D. K. and Ansari, M. A., “Autoencoders Based Deep Learner for Image Denoising,” Procedia Computer Science, 171: 1535–1541, (2020).
[6] Nishio, M., “Convolutional auto-encoders for image denoising of ultra-low-dose CT,” Heliyon, 3, (2017).
[7] Çetinkaya, E. and Kiraç, M. F., “Image denoising using deep convolutional autoencoder with feature pyramids,” Turkish Journal of Electrical Engineering and Computer Sciences, 28: 2096–2109, (2020).
[8] Kumar, A. and Sodhi, S. S., “Comparative Analysis of Gaussian Filter, Median Filter and Denoise Autoencoder,” in Proceedings of the 29 th International Conference on Machine Learning, 1627–1634, (2012).
[9] Gondara, L., “Medical Image Denoising Using Convolutional Denoising Autoencoders,” IEEE International Conference on Data Mining Workshops, ICDMW, 241–246, (2016).
[10] Zilvan, V., Ramdan, A., Suryawati, E., Kusumo, R. B. S., Krisnandi, D. and Pardede, H. F., “Denoising Convolutional Variational Autoencoders-Based Feature Learning for Automatic Detection of Plant Diseases,” ICICOS 2019 - 3rd International Conference on Informatics and Computational Sciences: Accelerating Informatics and Computational Research for Smarter Society in The Era of Industry 4.0, Proceedings, 0–5, (2019).
[11] Mohandas, A., Joseph, S. M. and Sathidevi, P. S., “An Autoencoder based Technique for DNA Microarray Image Denoising,” Proceedings of the 2020 IEEE International Conference on Communication and Signal Processing, ICCSP 2020, 1366–1371, (2020).
[12] Lee, D., Choi, S. and Kim, H. J., “Performance evaluation of image denoising developed using convolutional denoising autoencoders in chest radiography,” Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 884: 97–104, (2018).
[13] Hambal, A. M., Pei, Z. and Libent Ishabailu, F., “Image Noise Reduction and Filtering Techniques,” International Journal of Science and Research, 6: 2319–7064, (2015).
[14] D’Angelo, G. and Palmieri, F., “Network traffic classification using deep convolutional recurrent autoencoder neural networks for spatial–temporal features extraction,” Journal of Network and Computer Applications, 173, (2021).
[15] Attia, A. and Chaa, M., “Individual Recognition System using Deep network based on Face Regions,” International Journal of Applied Mathematics Electronics and Computers, 6: 27–32, (2018).
[16] Darici, M. B., Dokur, Z. and Olmez, T., “Pneumonia Detection and Classification Using Deep Learning on Chest X-Ray Images,” International Journal of Intelligent Systems and Applications in Engineering, 8: 177–183, (2020).
[17] Adweb, K. M. A., Cavus, N. and Sekeroglu, B., “Cervical Cancer Diagnosis Using Very Deep Networks over Different Activation Functions,” IEEE Access, 9: 46612–46625, (2021).
[18] Xu, B., Wang, N., Chen, T. and Li, M., “Empirical Evaluation of Rectified Activations in Convolutional Network,”, [Online]. Available: http://arxiv.org/abs/1505.00853 (2015).
[19] Yaqub, M., Feng, J., Zia, M., Arshid, K., Jia, K. and Rehman, Z., “State-of-the-art CNN optimizer for brain tumor segmentation in magnetic resonance images,” Brain Sciences, 10: 1–19, (2020).
[20] Ebrahimnejad, J. and Naghsh, A., “Removal of High-Density Salt-and-pepper Noise for Robust ROI Detection Used in Watermarking of MRI Images of the Brain,” Computers in Biology and Medicine, 137: 104831, (2021).
[21] Chen, M., Xu, Z., Weinberger, K. Q. and Sha, F., “Marginalized denoising autoencoders for domain adaptation,” Proceedings of the 29th International Conference on Machine Learning, ICML 2012, 1: 767–774, (2012).