Skip to main content

Advertisement

Springer Nature Link
Log in

Optimizing U-Net CNN performance: a comparative study of noise filtering techniques for enhanced thermal image analysis

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Infrared thermal imaging presents a promising avenue for detecting physiological phenomena such as hot flushes in animals, presenting a non-invasive and efficient approach for monitoring health and behavior. However, thermal images often suffer from various types of noise, which can impede the accuracy of analysis. In this study, the efficacy of different noise filtering algorithms is investigated utilizing filtering algorithms as preprocessing steps to enhance U-Net convolutional neural network (CNN) performance in processing animal skin infrared image sets for hot flush recognition. This study compares the performance of four commonly used filtering methods: mean, median, Gaussian, and bilateral filters. The impact of each filtering technique on noise reduction and preservation of features critical for hot flush detection is evaluated in a machine learning hot flush detection algorithm. The optimal filtering for skin thermal imaging was a median filter which significantly improved the U-Net CNN’s ability to accurately identify hot flush patterns, achieving an Intersection over Union score of 92.6% compared to 90.4% without filters. This research contributes to the advancement of thermal image processing methodologies for animal health monitoring applications, providing valuable insights for researchers and practitioners in the field of veterinary medicine and animal behavior studies utilizing autonomous thermal image segmentation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Data availability

The dataset used in this paper was created and analyzed by the authors themselves, with no external datasets utilized in this research.

References

  1. Petrou MM, Petrou C (2010) Image processing: the fundamentals. John Wiley & Sons

    Book  Google Scholar 

  2. Suganyadevi S, Seethalakshmi V, Balasamy K (2022) A review on deep learning in medical image analysis. Int J Multimed Info Retr 11(1):19–23

    Article  Google Scholar 

  3. Krawczyk JM, Mazur AM, Sasin T, Stokłosa AW (2015) Infrared building inspection with unmanned aerial vehicles. Prace Instytutu Lotnictwa 3(240):32–48

    Google Scholar 

  4. Jones BF, Plassmann P (2002) Digital infrared thermal imaging of human skin. IEEE Eng Med Biol Mag 21(6):41–48

    Article  Google Scholar 

  5. Merchenthaler I, Lane M, Stennett C, Zhan M, Nguyen V, Prokai-Tatrai K, Prokai L (2020) Brain-selective estrogen therapy prevents androgen deprivation-associated hot flushes in a rat model. Pharmaceuticals 13(6):119

    Article  Google Scholar 

  6. Merchenthaler I, Stennett CA, Haughey B, Puche A, Urbanski HF (2020) Establishment of a non-human primate model for menopausal hot flushes. EC Gynaecol 9(1)

  7. Ramesh S, Sasikala S, Paramanandham N (2021) Segmentation and classification of brain tumors using modified median noise filter and deep learning approaches. Multimed Tools Appl 80(8):11789–11813

    Article  Google Scholar 

  8. Chatterjee S, Thakur RS, Yadav RN, Gupta L, Raghuvanshi DK (2020) Review of noise removal techniques in ECG signals. IET Signal Proc 14(9):569–590

    Article  Google Scholar 

  9. S Bharati T Z Khan P Podder N Q Hung. 2021. A comparative analysis of image denoising problem: noise models, denoising filters and applications. Cognitive Internet of Medical Things for Smart Healthcare: Services and Applications. 49–66.

  10. Thakur RS, Chatterjee S, Yadav RN, Gupta L (2021) Image de-noising with machine learning: a review. IEEE Access 9:93338–93363

    Article  Google Scholar 

  11. D A Jassim S I Jassim N J Alhayani. 2022. Image De-Blurring and De-Noising by Using a Wiener Filter for Different Types of Noise. In International Conference on Emerging Technologies and Intelligent Systems. 451–460. Springer International Publishing. Cham

  12. K. S Sankaran P Manishankar K R Teja P K Reddy T P Kumar. 2020 Digital image de-noising and restoration method using differential filters for improving the image quality. In 2020 International Conference on Communication and Signal Processing (ICCSP) 1377–1380. IEEE

  13. A Krishhevsky I Sutskever G E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems. 25.

  14. Z W Yuan J Zhang 2016. Feature extraction and image retrieval based on AlexNet. In Eighth International Conference on Digital Image Processing (ICDIP 2016) 10033. 65–69. SPIE.

  15. Sarvamangala DR, Kulkarni RV (2022) Convolutional neural networks in medical image understanding: a survey. Evol Intel 15(1):1–22

    Article  Google Scholar 

  16. P Kapoor S V A V Prasad. 2010. Image processing for early diagnosis of breast cancer using infrared images. 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE).

  17. O Ronneberger P Fischer T Brox 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015, Proceedings, Part III 18. Springer International Publishing. 234–241

  18. Kuang X, Sui X, Liu Y, Chen Q, Gu G (2019) Single infrared image enhancement using a deep convolutional neural network. Neurocomputing 332:119–128

    Article  Google Scholar 

  19. Gonzalez, R. C. (2009). Digital image processing. Pearson education india.

  20. Baldridge AM, Hook SJ, Grove CI, Rivera G, Hulley GC (2009) The ASTER spectral library version 2 0. Remote Sens Environ 113(4):711–715

    Article  Google Scholar 

  21. Boardman JW (1997) Discrimination of subpixel spectral variability in hyperspectral image data: comparison of three methods. Remote Sens Environ 62(1):38–54. https://doi.org/10.1016/s0034-4257(97)00049-1

    Article  Google Scholar 

  22. Kusiak J, Piłat A, Piłat M, Szustakowski M, Zaborowicz M (2019) The influence of external factors on thermal camera calibration. Sensors 19(18):3947. https://doi.org/10.3390/s19183947

    Article  Google Scholar 

  23. Li H, Yan L, Liu J, Zhao Y (2018) Characterization of environmental effects on thermal remote sensing data. Remote Sensing 10(8):1228. https://doi.org/10.3390/rs10081228

    Article  Google Scholar 

  24. Mallick K, Bhattacharya AK (2015) Noise in thermal infrared images and its impact on target detection and identification. Def Sci J 65(3):197–204. https://doi.org/10.14429/dsj.65.8508

    Article  Google Scholar 

  25. Nandhini A, Ramesh MV (2017) Assessment of the impact of atmospheric variables on thermal infrared imagery using multiple regression analysis. ISPRS J Photogramm Remote Sens 123:16–24. https://doi.org/10.1016/j.isprsjprs.2016.11.009

    Article  Google Scholar 

  26. Avis NE, Crawford SL, Green R (2018) Vasomotor symptoms across the menopause transition: differences among women. Obstetrics and Gynecology Clinics 45(4):629–640

    Google Scholar 

  27. Freeman EW, Sammel MD, Sanders RJ (2014) Risk of long term hot flashes after natural menopause: evidence from the Penn Ovarian Aging Cohort. Menopause (New York, NY) 21(9):924

    Article  Google Scholar 

  28. Barbosa Pereira C, Kunczik J, Zieglowski L, Tolba R, Abdelrahman A, Zechner D, Vollmar B, Janssen H, Thum T, Czaplik M (2018) Remote welfare monitoring of rodents using thermal imaging. Sensors 18(11):3653

    Article  Google Scholar 

  29. Mota-Rojas D, Olmos-Hernández A, Verduzco-Mendoza A, Lecona-Butrón H, Martínez-Burnes J, Mora-Medina P, Orihuela A (2021) Infrared thermal imaging associated with pain in laboratory animals. Exp Anim 70(1):1–12

    Article  Google Scholar 

Download references

Acknowledgments

This research was supported by grant R01AG070072 from the NIH/NIA entitled ‘Brain-selective estrogen therapy for menopausal hot flushes in an advanced translational animal model.’

Author information

Authors and Affiliations

  1. Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, MD, USA

    Hamid Hoorfar & Istvan Merchenthaler

  2. Department of Neurobiology, University of Maryland School of Medicine, Baltimore, MD, USA

    Adam C. Puche

Authors
  1. Hamid Hoorfar
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Istvan Merchenthaler
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Adam C. Puche
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

The primary author of this manuscript is H.H., who provided the model and algorithm for image processing and machine learning. A.P. and I.M. served as supervisors, contributing to the review process, editing, and other related tasks associated with the paper.

Corresponding author

Correspondence to Hamid Hoorfar.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hoorfar, H., Merchenthaler, I. & Puche, A.C. Optimizing U-Net CNN performance: a comparative study of noise filtering techniques for enhanced thermal image analysis. J Supercomput 80, 23384–23406 (2024). https://doi.org/10.1007/s11227-024-06320-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-024-06320-5

Keywords