Modified Base Autoencoder and Variational Autoencoder for Denoising Images in CIFAR-10 and MNIST Datasets
Abstract
With the increasing volume of digital images, we must increase the quality of images for accuracy and visible applications, and we need ways to reduce the image noise while keeping important features such as edges, corners, and sharp details. In recent years, deep learning algorithms have become more significant for solving image denoising problems because they can simulate complex image patterns. This paper compares the performance of modified base AutoEncoders (AEs) and Variational Autoencoders (VAEs) models for image denoising in CIFAR-10 for color images and MNIST for grayscale images datasets. Our proposed modification to base AE and VAE architectures consists of changes in the encoder and decoder layers of feature extraction and reconstruction abilities, resulting in improved denoising performance. To simulate real-world image damages, data preparation involved normalization and the injection of Gaussian noise (0.5 for MNIST and 0.5 for CIFAR-10). With batch normalization and UpSampling2D layers with sigmoid outputs, the encoder-decoder architecture guaranteed the accuracy of spatial reconstruction, while VAE combined MSE with KL divergence for latent regularization, and AE optimized MSE reconstruction loss. The two models' performance was evaluated using important essential metrics: the Structural Similarity (SSIM) and the Peak Signal to Noise Ratio (PSNR). In both datasets, the results indicate that the VAE model outperforms the AE model in terms of image quality. The CIFAR-10 color dataset was given an SSIM of 0.954 and a PSNR of 32.86 dB, whereas the MNIST grayscale dataset provided an SSIM of 0.951 and a PSNR of 24.44 dB to the modified VAE model. In addition, the CIRAF-10 dataset achieved an SSIM of 0.891 and a PSNR of 27.72 dB, whereas the MNIST dataset was given an SSIM of 0.883 and a PSNR of 29.06 dB from the AE model. This study addresses how AE and VAE architectures differ in denoising performance across dataset complexities and the principles for optimal model selection.References
Alhijaj, J. A., & Khudeyer, R. S. (2023). Integration of efficientnetb0 and machine learning for fingerprint classification. Informatica, 47(5).
R. J. AL-Sukeinee and R. S. Khudeyer, "Review: Deep Learning and Fuzzy Logic Applications," Engineering and Technology Journal, vol. 9, no. 2456-3358, pp. 4231-4240, 2024.
R. Malhotra1, R. Malhotra and P. Singh, "Recent advances in deep learning models: a systematic," Mathematics, vol. 11, p. 1777, 2023.
K. Berahmand, F. Daneshfar2., S. S. Salehi, Y. Li1 and Y. Xu1, "Autoencoders and their applications in machine learning:" Artificial Intelligence Review, vol. 57, p. 28, 2024.
M. J. Kusner, B. Paige and J. M. Hernández-Lobato, "Grammar Variational Autoencoder," In International conference on machine learning, pp. 1945-1954, 2017
R. WEI, C. GARCIA, A. EL-SAYED, V. PETERSON and A. MAHMOOD, "Variations in Variational Autoencoders - A," comparative evaluation. Ieee Access, vol. 8, pp. 153651-153670, 2020.
B. Biswas and S. K. Ghosh, "DVAE: Deep Variational Auto-Encoders," Hybrid machine intelligence for medical image analysis, pp. 257-273, 2020.
M. Sreeteish, A. Mohammed, S. S. Reddy and C. N. Sujatha, "Image De-Noising Using Convolutional Variational," International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 10, 2022.
A. Raj1, A. A. Jadhav, C. G. Bhimrao and D. J. Anil, "Image Denoising Using Python and Machine," International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 11, 2023.
S. Singh and D. R. Gupta, "Comparative Analysis of Deep Learning-Based," International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 12, 2024.
B. Biswas, S. K. Ghosh and A. Ghosh, "DVAE: deep variational auto-encoders for denoising retinal fundus image," Hybrid machine intelligence for medical image analysisز, pp. 257-273, 2020.
Pawar, Aashay." Noise reduction in images using autoencoders.," 3rd International Conference on Intelligent Sustainable Systems (ICISS)., pp. 987-990, 2020.
M. Prakash, A. Krull and F. Jug, "Fully Unsupervised Diversity," arXiv preprint arXiv:2006.06072, 2020.
P. Venkataraman, "Image Denoising Using Convolutional Autoencoder," arXiv:2207.11771, 2022.
H. V. Guleria, A. M. Luqmani, H. D. Kothari, P. Phukan, S. Patil, P. Pareek, K. Kotecha, A. Abraham and. L. A. Gabralla, "Enhancing the Breast Histopathology Image Analysis for Cancer Detection Using Variational Autoencoder," International Journal of Environmental Research and Public Health, vol. 20, no. 5, p. 4244, 2023.
M. B. DARICI and Z. ERDEM, "A Comparative Study on Denoising from Facial Images Using Convolutional," Gazi University Journal of Science, vol. 36, no. 3, pp. 1122-1138, 2023.
S. R. Tusher, N. N. Rahman, S. Chowdhury, A. Tabassum, A. Adnan, . R. Rahman and S. R. Al Masud, "An Enhanced Variational AutoEncoder Approach for the Purpose of Deblurring Bangla License Plate," International Journal of Advanced Computer Science and Applications, vol. 14, no. 6, pp. 10-14569, 2023.
O. J. Bartlett, D. M. Benoit, K. A. Pimbblet, B. Simmons and L. Hunt, "Noise reduction on single-shot images using an autoencoder," Monthly Notices of the Royal Astronomical Society, vol. 52, no. 4, pp. 6318-6329, 2023.
Y. FAROOQ and S. SAVAŞ, "Noise Removal from the Image Using Convolutional Neural Networks-Based Denoising Auto Encoder " journal of Emerging Computer Technologies., vol. 3, no. 1, pp. 21-28, 2024.
K. Kea, W.-D. Chang, H. C. Park and Y. Han, "Enhancing a Convolutional Autoencoder with a Quantum Approximate Optimization Algorithm for Image Noise Reduction," arXiv preprint arXiv:2401.06367, 2024.
R. Malhotra and P. Singh, "Recent advances in deep learning models: a systematic literature review,”. Multimedia Tools and Applications., vol. 82, no. 29, pp. 44977-45060, 2023.
M. Sewak, S. K. Sahay and. H. Rathore, "An Overview of Deep Learning Architecture of Deep Neural," Journal of Computational and Theoretical Nanoscience, vol. 17, no. 1, pp. 182188, 2020.
A. Solera-Rico, C. S. Vila, M. Gómez-López, Y. Wang, A. Almashjary, S. T. M. Dawson and R. Vinuesa, "β-Variational autoencoders and transformers for reduced-order modelling of fluid flows," Nature Communications, vol. 15, no. 1, p. 1361, 2024.
M. S. Rana, M. H. Kabir and A. Sobur, "Comparison of the Error Rates of MNIST Datasets Using Different Type of Machine Learning Model," North American Academic Research, vol. 6, no. 5, pp. 173-181, 2022.
M. Kundroo and T. Kim, "Demystifying Impact of Key Hyper-Parameters in Federated Learning:
A Case Study on CIFAR-10 and FashionMNIST," IEEE Access, 2024.
K. A. Alaghbari, H.-S. Lim, M. H. M. Saad and Y. S. Yong, "Deep Autoencoder-Based Integrated Model for Anomaly," IoT, vol. 4, no. 3, pp. 345-365, 2023.
C. J. Harvey, S. Shomaji, Z. Yao, M. I. and A. Noheria, "Comparison of Autoencoder Encodings for ECG Representation in Downstream Prediction Tasks," arXiv preprint arXiv:2410.02937, 2024.
M. B. DARICI and Z. ERDEM, "A Comparative Study on Denoising from Facial Images Using Convolutional Autoencoder," Gazi University Journal of Science, vol. 36, no. 3, pp. 11221138, 2023.
DOI:
https://doi.org/10.31449/inf.v49i27.9620Downloads
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
