Advanced CNN-Based Image Denoising Techniques for Digital Forensics Applications
Received: 17 February 2026 | Revised: 22 March 2026 and 2 April 2026 | Accepted: 3 April 2026 | Online: 21 April 2026
Corresponding author: H. S. Annapurna
Abstract
In digital forensics, image denoising is essential because the caliber and clarity of visual evidence have a strong influence on the results of investigations and court cases. Gaussian noise, salt-and-pepper noise, Poisson noise, and speckle noise are just a few of the noise types that are frequently introduced during the collection, transmission, or storage of forensic photographs. Although computationally efficient, traditional denoising techniques, such as median filtering and bilateral filtering, frequently lose edge information and small features that are essential for forensic investigation. This study suggests a sophisticated Convolutional Neural Network (CNN) architecture that includes adversarial training elements, multi-scale processing, residual learning, and attention processes, especially tailored for forensic picture denoising. The proposed approach successfully reduces noise across a variety of noise kinds and intensity levels while preserving evidentiary integrity, addressing the difficulties of forensic imaging. The superiority of the suggested method is demonstrated by extensive experimental validation on standard datasets such as MNIST, BSD68, and Set12, yielding Structural Similarity Index Measure (SSIM) scores of 0.92 and Peak Signal-to-Noise Ratio (PSNR) improvements of 10.2 dB over noisy inputs, significantly outperforming traditional methods. With an average inference time of 0.02 s per image on typical GPU hardware, the model demonstrates computational efficiency and is appropriate for real-time forensic applications. A comparison with cutting-edge methods confirms the suggested approach's resilience and capacity for generalization in a variety of forensic contexts.
Keywords:
image denoising, digital forensics, convolutional neural networks, residual learning, attention mechanisms, deep learning, image quality enhancement, forensic evidence analysisDownloads
References
S. Rani, Y. Chabrra, and K. Malik, "An Improved Denoising Algorithm for Removing Noise in Color Images," Engineering, Technology & Applied Science Research, vol. 12, no. 3, pp. 8738–8744, June 2022.
A. E. Ilesanmi and T. O. Ilesanmi, "Methods for image denoising using convolutional neural network: a review," Complex & Intelligent Systems, vol. 7, no. 5, pp. 2179–2198, Oct. 2021.
M. Shafiq and Z. Gu, "Deep Residual Learning for Image Recognition: A Survey," Applied Sciences, vol. 12, no. 18, Sept. 2022, Art. no. 8972.
C. Tian, L. Fei, W. Zheng, Y. Xu, W. Zuo, and C. W. Lin, "Deep learning on image denoising: An overview," Neural Networks, vol. 131, pp. 251–275, Nov. 2020.
M. Zanardelli, F. Guerrini, R. Leonardi, and N. Adami, "Image forgery detection: a survey of recent deep-learning approaches," Multimedia Tools and Applications, vol. 82, no. 12, pp. 17521–17566, May 2023.
I. Goodfellow et al., "Generative adversarial networks," Communications of the ACM, vol. 63, no. 11, pp. 139–144, Oct. 2020.
C. Tian, Y. Xu, and W. Zuo, "Image denoising using deep CNN with batch renormalization," Neural Networks, vol. 121, pp. 461–473, Jan. 2020.
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, Mar. 2024.
R. Kaur, G. Karmakar, and M. Imran, "Impact of Traditional and Embedded Image Denoising on CNN-Based Deep Learning," Applied Sciences, vol. 13, no. 20, Oct. 2023, Art. no. 11560.
B. Goyal, A. Dogra, S. Agrawal, B. S. Sohi, and A. Sharma, "Image denoising review: From classical to state-of-the-art approaches," Information Fusion, vol. 55, pp. 220–244, Mar. 2020.
S. Zhang, C. Liu, Y. Zhang, S. Liu, and X. Wang, "Multi-Scale Feature Learning Convolutional Neural Network for Image Denoising," Sensors, vol. 23, no. 18, Sept. 2023, Art. no. 7713.
S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, "CBAM: Convolutional Block Attention Module," in Computer Vision – ECCV 2018, vol. 11211, V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Eds. Springer International Publishing, 2018, pp. 3–19.
A. M. Ali, B. Benjdira, A. Koubaa, W. El-Shafai, Z. Khan, and W. Boulila, "Vision Transformers in Image Restoration: A Survey," Sensors, vol. 23, no. 5, Feb. 2023, Art. no. 2385.
Y. Cui, M. Shi, and J. Jiang, "Multi-Scale Detail–Noise Complementary Learning for Image Denoising," Applied Sciences, vol. 14, no. 16, Aug. 2024, Art. no. 7044.
M. T. Duong, B. T. Nguyen Thi, S. Lee, and M. C. Hong, "Multi-Branch Network for Color Image Denoising Using Dilated Convolution and Attention Mechanisms," Sensors, vol. 24, no. 11, June 2024, Art. no. 3608.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998.
"MNIST Database of Handwritten Digits." UCI Machine Learning Repository, 1998.
D. Martin, C. Fowlkes, D. Tal, and J. Malik, "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics," in Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001, vol. 2, pp. 416–423.
"clausmichele/CBSD68-dataset." [Online]. Available: https://github.com/clausmichele/CBSD68-dataset.
K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising," IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142–3155, July 2017.
"datasets/Set12," GitLab. https://plmlab.math.cnrs.fr/matias.tassano/dct-cnn/-/tree/master/datasets/Set12?ref_type=heads.
H. Liu, Z. Li, S. Lin, and L. Cheng, "A Residual UNet Denoising Network Based on Multi-Scale Feature Extraction and Attention-Guided Filter," Sensors, vol. 23, no. 16, Aug. 2023, Art. no. 7044.
P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, "Image-to-Image Translation with Conditional Adversarial Networks," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, pp. 5967–5976.
Downloads
How to Cite
License
Copyright (c) 2026 H. S. Annapurna, K. Mala, Gousia Thahniyath, V. C. Rudramurthy, T. G. Mohan Kumar, G. K. Shwetha
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
