SavedAdd your journal

Journals / Teknik Meslek Yüksekokulları Akademik Araştırma Dergisi / 2026 / Cilt: 5 Sayı: 1

Mitigating Periodic Noise in Digital Images Using a Deep Learning-Based Hybrid Model

Derin Öğrenme Tabanlı Hibrit Model ile Dijital Görüntülerde Periyodik Gürültülerin Giderilmesi

Murat Altunok(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ, MÜHENDİSLİK VE MİMARLIK FAKÜLTESİ, BİLGİSAYAR MÜHENDİSLİĞİ BÖLÜMÜ, BİLGİSAYAR MÜHENDİSLİĞİ PR.)0000-0002-2756-2586
Bülent Turan(SİVAS CUMHURİYET ÜNİVERSİTESİ, SİVAS TEKNİK BİLİMLER MESLEK YÜKSEKOKULU, ELEKTRİK VE ENERJİ BÖLÜMÜ)0000-0003-0673-469X
Pages
113–126
Publication Date
2026-06-04
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The findings indicate that the hybrid method achieved maximum values of 38.15 dB PSNR and 0.96 SSIM, demonstrating that it not only effectively mitigates noise but also maintains the structural integrity of the images.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study proposes a deep learning-based hybrid method for the removal of periodic noise frequently encountered in digital images.
📊
Key Findings & Data:The model was trained on a dataset consisting of synthetically generated images containing various types of periodic noise.
💡
Conclusion & Impact:The findings indicate that the hybrid method achieved maximum values of 38.15 dB PSNR and 0.96 SSIM, demonstrating that it not only effectively mitigates noise but also maintains the structural integrity of the images.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Periyodik gürültü · Gürültü Giderme Yöntemleri · Derin Öğrenme

Abstract

This study proposes a deep learning-based hybrid method for the removal of periodic noise frequently encountered in digital images. Periodic noise degrades image quality and complicates analysis and interpretation processes. The limited success of traditional filtering techniques in handling such noise highlights the need for more effective solutions. In the proposed approach, the first stage involves identifying noise peak points in the frequency domain using Fourier Transform, followed by statistical denoising with a notch filter. In the second stage, the DnCNN (Denoising Convolutional Neural Network) model is applied to eliminate residual noise components and minimize detail loss. The model was trained on a dataset consisting of synthetically generated images containing various types of periodic noise. The performance of the method was evaluated using PSNR and SSIM metrics. The findings indicate that the hybrid method achieved maximum values of 38.15 dB PSNR and 0.96 SSIM, demonstrating that it not only effectively mitigates noise but also maintains the structural integrity of the images. Compared to traditional methods, the proposed model achieved more consistent and successful outcomes, showing high performance across different types of periodic noise. In this context, the study offers an effective and practical approach for removing periodic noise in image processing and establishes a solid basis for subsequent research on deep learning-based denoising methods.

Özet

Bu çalışma, dijital görüntülerde sıkça karşılaşılan periyodik gürültülerin giderilmesine yönelik derin öğrenme tabanlı hibrit bir yöntem önermektedir. Periyodik gürültü, görüntü kalitesini düşürerek analiz ve yorum süreçlerini güçleştirir. Geleneksel filtreleme yöntemlerinin bu tür gürültüler üzerinde sınırlı başarı sağlaması, daha etkili tekniklerin geliştirilmesini gerekli kılmıştır. Önerilen yöntemde, ilk aşamada Fourier dönüşümü yardımıyla frekans alanındaki gürültü tepe noktaları belirlenmiş ve bu bölgeler çentik filtresi ile istatistiksel olarak temizlenmiştir. İkinci aşamada ise DnCNN (Denoising Convolutional Neural Network) modeli uygulanarak görüntüde kalan gürültü bileşenleri giderilmiş ve detay kaybı en aza indirilmiştir. Modelin eğitimi, sentetik olarak oluşturulan ve farklı türde periyodik gürültülerin uygulandığı veri setleri üzerinde gerçekleştirilmiştir. Elde edilen sonuçlar, PSNR ve SSIM metrikleriyle değerlendirilmiş; hibrit yöntemin en yüksek 38,15 dB PSNR ve 0,96 SSIM değerlerine ulaştığı ve yalnızca gürültüyü azaltmakla kalmayıp, aynı zamanda görüntülerin yapısal bütünlüğünü koruduğu görülmüştür. Önerilen model, geleneksel yöntemlere kıyasla daha tutarlı ve başarılı sonuçlar üretmiş, farklı periyodik gürültü türlerinde yüksek performans sergilemiştir. Bu yönüyle çalışma, görüntü işleme alanında derin öğrenme destekli periyodik gürültü giderimi için etkili ve uygulanabilir bir çözüm sunmakta, gelecekteki araştırmalar için de güçlü bir temel oluşturmaktadır.

🔖

Cite This Article

Altunok, M., Turan, B. (2026). Mitigating Periodic Noise in Digital Images Using a Deep Learning-Based Hybrid Model. Teknik Meslek Yüksekokulları Akademik Araştırma Dergisi, Cilt: 5 Sayı: 1, 113–126. https://ajindex.com/articles/1626571

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (51)

  1. Abdulah CS, Rohani MN, Ismail B, Isa MA, Rosmi AS, Mustafa WA. 2021. Comparison of Image Restoration Using Median, Wiener and Gaussian Filtering Techniques Based on Electrical Tree, In: 2021 IEEE Industrial Electronics and Applications Conference (IEACon), ss. 163-168.
  2. Abu-Ein AAK. 2013. A Novel Methodology for Digital Removal of Periodic Noise Using 2D Fast Fourier Transforms, Contemporary Engineering Sciences, 6(3): 103-116.
  3. Afshari HH, Gadsden A, Habibi S. 2017. Gaussian Filters For Parameter and State Estimation: A General Review of Theory and Recent Trends, Signal Processing, 135: 218-238.
  4. Aghajarian M, McInroy JE, Muknahallipatna S. 2020. Deep Learning Algorithm For Gaussian Noise Removal From Images, Journal of Electronic Imaging, 29(4): 043005-043005.
  5. Aizenberg I, Butakoff C. 2002. Frequency Domain Medianlike Filter For Periodic and Quasi-Periodic Noise Removal, Image Processing: Algorithms and Systems, 181-191.
  6. Alawode BO, Masood M, Ballal T, Al-Naffouri T. 2021. Dense-Sparse Deep CNN Training for Image Denoising, arXiv Preprint, arXiv:2107.04857.
  7. Alibabaie N, Latif A. 2021. Adaptive Periodic Noise Reduction in Digital Images Using Fuzzy Transform, Journal of Mathematical Imaging and Vision, 63(4): 503-527.
  8. Alolaiwy M, Tanik M, Jololian L. 2021. From CNNs to Adaptive Filter Design for Digital Image Denoising Using Reinforcement Q-Learning, In: SoutheastCon, ss. 1-8.
  9. Altunok M, Turan B. 2022. Periyodik Gürültü Tipleri ve Yapısal Özellikleri, Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 15(2): 140-150.
  10. Asarkaya S, Ünsal E. 2022. Akıllı Sensör Verileri Üzerinde Makine Öğrenmesi Yöntemleri Kullanılarak İnsan Aktivitelerinin Tanımlanması, Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi, 1(1): 9-14.
  11. Boyat AK, Brijendra KJ. 2015. A Review Paper: Noise Models in Digital Image Processing, Signal & Image Processing: An International Journal, 6(3): 63-75.
  12. Carvalho Â, Esteves T, Quelhas P, Monteiro FJ. 2018. MobilityAnalyser: A Novel Approach for Automatic Quantification of Cell Mobility on Periodic Patterned Substrates Using Brightfield Microscopy Images, Computer Methods and Programs in Biomedicine, 162: 61-67.
  13. Chandel R, Gupta G. 2013. Image Filtering Algorithms and Techniques: A Review, International Journal of Advanced Research in Computer Science and Software Engineering, 3(10): 198-202.
  14. Chen J, Chen J, Chao H, Yang M. 2018. Image Blind Denoising with Generative Adversarial Network Based Noise Modeling, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, ss. 3155-3164.
  15. Chen Y, Huang TZ, Zhao XL, Deng LJ, Huang J. 2017. Stripe Noise Removal of Remote Sensing Images by Total Variation Regularization and Group Sparsity Constraint, Remote Sensing, 9(6): 559.
  16. Deng J, Hu C. 2024. Recovering a Clean Background: A New Progressive Multi-Scale CNN for Image Denoising, Signal, Image and Video Processing, 18(1): 1-12.
  17. Duran O, Turan B, Kaya M. 2025. Machine-Learning-Based Ensemble Regression for Vehicle-to-Vehicle Distance Estimation Using a Toe-In Style Stereo Camera, Measurement, 240: 115540.
  18. Dutta S, Mallick A, Roy S, Kumar U. 2014. Periodic Noise Recognition and Elimination Using RFPCM Clustering, In: 2014 International Conference on Electronics and Communication Systems (ICECS), ss. 1-5.
  19. Erol A, Gürbüz ME, Gangal A. 2016. Video Görüntülerindeki Periyodik Gürültülerin Yok Edilmesi, ResearchGate, ss. 535-537.
  20. Fan L, Zhang F, Fan H, Zhang C. 2019. Brief Review of Image Denoising Techniques, Visual Computing for Industry, Biomedicine and Art, 2: 2-7.
  21. Gonzalez R, Woods R. 2008. Digital Image Processing, Pearson Education, Inc., New Jersey.
  22. Güneş A, Çetin Kaya Y. 2024. Evrişimsel Sinir Ağları ile Görüntülerde Gürültü Türünü Saptama, Bilgisayar Bilimleri ve Mühendisliği Dergisi, 17(1): 75-89.
  23. Guttman N, Julesz B. 1963. Lower Limits of Auditory Periodicity Analysis, Journal of the Acoustical Society of America, 35(5): 610.
  24. Hu G, Yang Y, Yi D, Kittler J, Christmas W, Li Z, Hospedales T. 2015. When Face Recognition Meets With Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition, In: Proceedings of the IEEE International Conference on Computer Vision Workshops, ss. 142-150.
  25. Ionita MG, Coanda HG. 2017. Automatic Periodic Noise Removal in Microscopy Images, In: 2017 International Symposium on Signals, Circuits and Systems (ISSCS), ss. 1-4.
  26. İnik Ö, Turan B. 2018. Classification of Animals with Different Deep Learning Models, Journal of New Results in Science, 7(1): 9-16.
  27. İnik Ö, Ülker E. 2017. Derin Öğrenme ve Görüntü Analizinde Kullanılan Derin Öğrenme Modelleri, Gaziosmanpaşa Bilimsel Araştırma Dergisi, 6(3): 85-104.
  28. Kang X, Li YL, Qu Z, Jiwu H. 2011. Enhancing Source Camera Identification Performance With a Camera Reference Phase Sensor Pattern Noise, IEEE Transactions on Information Forensics and Security, 6(2): 393-402.
  29. Kaya M, Ulutürk S, Çetin Kaya Y, Altıntaş O, Turan B. 2023. Optimization of Several Deep CNN Models for Waste Classification, SAUCIS, ss. 91-104.
  30. Ketenci S, Gangal A. 2017. Automatic Reduction of Periodic Noise in Images Using Adaptive Gaussian Star Filter, Turkish Journal of Electrical Engineering and Computer Sciences, 25(3): 2336-2348.
  31. Khan A, Sohail A, Zahoora U, Qureshi AS. 2020. A Survey of the Recent Architectures of Deep Convolutional Neural Networks, Artificial Intelligence Review, 53(8): 5455-5516.
  32. Krizhevsky A, Sutskever I, Hinton GE. 2012. ImageNet Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems, 25.
  33. Krull A, Buchholz TO, Jug F. 2019. Noise2Void - Learning Denoising From Single Noisy Images, In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), ss. 2129-2137.
  34. Küpeli C, Bulut F. 2020. Görüntüdeki Tuz Biber ve Gauss Gürültülerine Karşı Filtrelerin Performans Analizleri, Haliç Üniversitesi Fen Bilimleri Dergisi, 3(2): 211-239.
  35. Le T, Chartrand R, Asaki TJ. 2007. A Variational Approach to Reconstructing Images Corrupted by Poisson Noise, Journal of Mathematical Imaging and Vision, 27(3): 257-263.
  36. LeCun Y, Bottou L, Bengio Y, Haffner P. 1998. Gradient Based Learning Applied to Document Recognition, Proceedings of the IEEE, 86(11): 2278-2324.
  37. Lehtinen J, Munkberg J, Hasselgren J, Laine S, Karras T, Aittala M, Aila T. 2018. Noise2Noise: Learning Image Restoration without Clean Data, In: Proceedings of the 35th International Conference on Machine Learning (ICML), ss. 2965-2974.
  38. Li B, Zhang Y, Chen W, Ma Y, Li L. 2024. Neural Network-Based Investigation of Periodic Noise Reduction Methods for High-Resolution Infrared Line Scanning Images, Remote Sensing, 16(5): 841.
  39. McCulloch W, Pitts W. 1943. A Logical Calculus of the Ideas Immanent in Nervous Activity, The Bulletin of Mathematical Biophysics, 5(4): 115-133.
  40. Moallem P, Masoumzadeh M, Habibi M. 2015. A Novel Adaptive Gaussian Restoration Filter for Reducing Periodic Noises in Digital Image, Signal, Image and Video Processing, 9(5): 1179-1191.
  41. Novikov A, Pronkin A, Vityazev S. 2022. Edge Detector Application in the Problem of Periodic Interference Filtering, In: 2022 24th International Conference on Digital Signal Processing and its Applications (DSPA), ss. 1-6.
  42. Saadia A, Rashdi A. 2018. A Speckle Noise Removal Method, Circuits Systems and Signal Processing, 37(6): 2639-2650.
  43. Tian C, Zheng M, Zuo W, Zhang B, Zhang Y, Zhang D. 2023. Multi-Stage Image Denoising with the Wavelet Transform, Pattern Recognition, 134: 1-12.
  44. Varghese J. 2016. Adaptive Threshold Based Frequency Domain Filter for Periodic Noise Reduction, AEU-International Journal of Electronics and Communications, 70(12): 1692-1701.
  45. Varghese JS, Subramaniam K, Palaniswamy KS. 2020. Adaptive Gaussian Notch Filter for Removing Periodic Noise from Digital Images, IET Image Processing, 14(8): 1529-1538.
  46. Vyas A, Yu S, Paik J. 2018. Multiscale Transforms with Application to Image Processing, Springer, Singapore.
  47. Wang J, Liu DC. 2010. 2-D FFT for Periodic Noise Removal on Strain Image, In: 2010 4th International Conference on Bioinformatics and Biomedical Engineering, ss. 1-4.
  48. Wei Z, Wang J, Nichol H, Wiebe S, Chapman D. 2012. A Median-Gaussian Filtering Framework for Moiré Pattern Noise Removal from X-Ray Microscopy Image, Micron, 43(2-3): 170-176.
  49. Xie Y, Chen L, Hofmann U. 2012. Reduction of Periodic Noise in Fourier Domain Optical Coherence Tomography Images by Frequency Domain Filtering, Biomedical Engineering / Biomedizinische Technik, 57(S1): 830-832.
  50. Yapıcı A, Akcayol MA. 2022. Derin Öğrenme ile Görüntülerde Gürültü Azaltma Üzerine Kapsamlı Bir İnceleme, International Journal of Advances in Engineering and Pure Sciences, 34(1): 65-90.
  51. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. 2017. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising, IEEE Transactions on Image Processing, 26(7): 3142-3155.