Abstract
Deep reinforcement learning (DRL), where an agent learns behaviors in an environment by actions and receiving rewards, has been applied successfully in the robotics area and game controllers at a human level. However, the application of DRL in image processing is still scarce. In this paper, we present a novel approach for image denoising by combining a fully connected network with the gated recurrent unit in an asynchronous advantage actor-critic scheme. The proposed method assigns an agent to every pixel of the input image, and the agent changes the value of each pixel by selecting an action from a predefined list. The goal is to learn an optimal policy to maximize the reward at all pixels of the image. We conduct the denoising experiments on the BSD68 dataset and the results show that the proposed approach produces equivalent or higher PSNR scores compared to several state-of-the-art models based on supervised learning. Our approach is interpretable to humans by showing the agent’s actions, which is a significant difference from original CNNs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Harold, B., Christian, S., Stefan, H.: Image denoising: can plain neural networks compete with BM3D? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2392–2399. IEEE (2012)
Cao, Q., Lin, L., Shi, Y., Liang, X., Li, G.: Attention-aware face hallucination via deep reinforcement learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 690–698. IEEE (2017)
Yunjin, C., Thomas, P.: Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 6, 1256–1272 (2016)
Kostadin, D., Alessandro, F., Vladimir, K., Karen, E.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 8, 2080–2095 (2007)
Gu, S., Zhang, L., Zuo, W., Feng, X.: Weighted nuclear norm minimization with application to image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2862–2869. IEEE (2014)
Huang, K., Li, D., Wu, H., Zhang, J.: A2-RL: aesthetics aware reinforcement learning for automatic image cropping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8193–8201. IEEE (2018)
Park, J., Lee, J.-Y., Yoo, D., So, K.I.: Distort-and-recover: color enhancement using deep reinforcement learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5928–5936. IEEE (2018)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Zhang, K., Zuo, W., Gu, S., Zhang, L.: Learning deep CNN denoiser prior for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3929–3938. IEEE (2017)
Acknowledgements
This research is partially supported by the Ministry of Science and ICT, Korea, under GITRC (IITP-2022-2015-0-00742), ICT Creative Consilience program (IITP-2022-2020-0-01821), and Artificial Intelligence Innovation Hub (No. 2021-0-02068).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bui, PN., Vo, VV., Le, DT., Choo, H. (2022). Image Denoising Using Fully Connected Network with Reinforcement Learning. In: Dang, T.K., Küng, J., Chung, T.M. (eds) Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications. FDSE 2022. Communications in Computer and Information Science, vol 1688. Springer, Singapore. https://doi.org/10.1007/978-981-19-8069-5_46
Download citation
DOI: https://doi.org/10.1007/978-981-19-8069-5_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8068-8
Online ISBN: 978-981-19-8069-5
eBook Packages: Computer ScienceComputer Science (R0)