Theoretical and Natural Science
- The Open Access Proceedings Series for Conferences
Theoretical and Natural Science
Vol. 18, 08 December 2023
Open
Access | Article
Autoencoders and their application in removing masks
* Author to whom correspondence should be addressed.
Abstract
Images are frequently distorted by noises that have a negative impact on the quality of image data. In this study, the author focuses on coping with a specific type of noise that has arisen regularly in recent years as a result of the pandemic: masks covering portions of the photographs of human faces. The paper employs the autoencoder model, which offers unsupervised learning. It compresses or encodes original data input into a smaller latent vector, then decodes it back to its original size, learning and extracting relevant features from the data in the process. In a further phase, the author employs a combination of convolutional autoencoders and denoising autoencoders, treating masks as corruptions in order to get more accurate predictions regarding the image of a human face without any covering. After training on 2,500 image pairs with and without masks and validating on 200 such image pairs, the model presented in this research achieves an overall accuracy of 93%. The research demonstrates that the combination of convolutional and denoising autoencoders is an excellent method for removing masks from facial images, and the author believes it can also be used to effectively remove other types of noise. However, the study also reveals that the picture data generated in this manner are always inferior to the original, and that the autoencoder can only process data of the same or comparable type on which it has been trained. In the future, improved models will exist to address these shortcomings and be applied to more real-life situations.
Keywords
convolutional autoencoders, denoising autoencoders, denoising, image reconstruction, mask-removing
References
1. He Chuan, Hu Changhua, Qi Naixin, et al. Fast proximal splitting algorithm for constrained TGV-regularised image restoration and reconstruction[J]. IET Image Processing, 2019, 13(4): 576-582
2. Chervinskii. Own work. CC BY-SA 4.0. 2015.
3. Kramer, Mark A. "Nonlinear principal component analysis using autoassociative neural networks" (PDF). AIChE Journal, 1991, 37 (2): 233–243.
4. Daniel Nelson. What is an Autoencoder. 2020. www.unite.ai.
5. Guo, Xifeng & Liu, Xinwang & Zhu, En & Yin, Jianping. Deep Clustering with Convolutional Autoencoders. 2017: 373-382.
6. Lilian Weng. From Autoencoder to Beta-VAE. lilianweng.github.io, 2018
7. Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron. Deep Learning. MIT Press, 2016.
8. Vincent, Pascal; Larochelle, Hugo. "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion". Journal of Machine Learning Research, 2010, 11: 3371–3408.
9. Wikipedia contributors, "Autoencoder," Wikipedia, The Free Encyclopedia, https://en.wikipedia.org/w/index.php?title=Autoencoder&oldid=1109263923 (accessed September 28, 2022).
Data Availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).
- Volume Title
- Proceedings of the 2nd International Conference on Computing Innovation and Applied Physics
- ISBN (Print)
- 978-1-83558-201-5
- ISBN (Online)
- 978-1-83558-202-2
- Published Date
- 08 December 2023
- Series
- Theoretical and Natural Science
- ISSN (Print)
- 2753-8818
- ISSN (Online)
- 2753-8826
- DOI
- 10.54254/2753-8818/18/20230352
- Copyright
- 08 December 2023
- Open Access
- This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited