EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advanced CNN-Based Image Denoising Techniques for Digital Forensics Applications

H. S. Annapurna, K. Mala, Gousia Thahniyath, V. C. Rudramurthy, T. G. Mohan Kumar, G. K. Shwetha

Engineering, Technology & Applied Science Research · 06.06.2026 · 16 (3) · 35448-35453

DOI: 10.48084/etasr.18234 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 06.06.2026. Verfasst von H. S. Annapurna und 5 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Annapurna, H. S., Mala, K., Thahniyath, G., Rudramurthy, V. C., Kumar, T. G. M., & Shwetha, G. K. (2026). Advanced CNN-Based Image Denoising Techniques for Digital Forensics Applications. Engineering, Technology & Applied Science Research, 16(3), 35448-35453. https://doi.org/10.48084/etasr.18234

Vancouver

Annapurna HS, Mala K, Thahniyath G, Rudramurthy VC, Kumar TGM, Shwetha GK. Advanced CNN-Based Image Denoising Techniques for Digital Forensics Applications. Engineering, Technology & Applied Science Research. 2026;16(3):35448-35453. doi:10.48084/etasr.18234

BibTeX
@article{Annapurna2026,
  author = {Annapurna, H. S. and Mala, K. and Thahniyath, Gousia and Rudramurthy, V. C. and Kumar, T. G. Mohan and Shwetha, G. K.},
  title = {Advanced CNN-Based Image Denoising Techniques for Digital Forensics Applications},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {3},
  pages = {35448--35453},
  doi = {10.48084/etasr.18234}
}
Kostenlos starten →