Image Quality Assessment for Gaussian Blur using Siamese Network combined with ResNet-18

  • Emrah Arslan Department of Computer Engineering, Faculty of Engineering, KTO Karatay University, Konya 42020, Turkey
  • Omid Zare Department of Computer Science, University of Verona, Verona 37134, Italy
  • Zeinab Mohseni Department of Computer Engineering, Faculty of Engineering, University of Birjand, Birjand 9717434765, Iran
  • Mahdi Beigzadeh Department of Computer Science, University of Verona, Verona 37134, Italy
  • Abel Abebe Bzuayene Department of Computer Science, University of Verona, Verona 37134, Italy
  • Ali Abbaszadeh Sori Department of Computer Engineering, Babol Branch, Islamic Azad University, Babol 3738147471, Iran
  • Javad Hassannataj Joloudari Department of Computer Engineering, Faculty of Engineering, University of Birjand, Birjand 9717434765, Iran; Department of Computer Engineering, Babol Branch, Islamic Azad University, Babol 3738147471, Iran; Department of Computer Engineering, Technical and Vocational University (TVU), Tehran 4631964198, Iran
  • Bulbula Kumeda Kussia Department of Computer Science, Jinka University, Jinka 165, Ethiopia
Article ID: 4668
35 Views
DOI: https://doi.org/10.18282/aii4668
Keywords: image quality assessment; siamese networks; gaussian blur; ResNet-18; full-reference IQA; deep learning

Abstract

This paper presents a novel Image Quality Assessment (IQA) framework, SNR (Siamese Network with ResNet-18), specifically designed for Gaussian blur detection. The approach leverages a Siamese network architecture combined with the ResNet-18 backbone to process image pairs—one blurred and one reference—to predict image quality based on their differences. The model effectively captures high-frequency features lost due to blur, such as edges and gradients. We conduct extensive experiments on the TID2013 dataset, showing that SNR achieves superior performance in blur-specific IQA tasks compared to other full-reference methods. Data augmentation techniques significantly improve model generalization, resulting in a test accuracy of 97.37% for ResNet-18. The proposed method demonstrates a strong correlation with human judgment and robust generalization across various image contents, with future work focusing on expanding its applicability to other distortions and optimizing computational efficiency.

Published
2025-05-04
How to Cite
Arslan, E., Zare, O., Mohseni, Z., Beigzadeh, M., Abebe Bzuayene, A., Abbaszadeh Sori, A., Hassannataj Joloudari, J., & Kumeda Kussia, B. (2025). Image Quality Assessment for Gaussian Blur using Siamese Network combined with ResNet-18. AI Insights, 1(2), 4668. https://doi.org/10.18282/aii4668
Issue
Vol. 1 No. 2 (2025)
Section
Article

References

1. Narvekar, N.D., Karam, L.J. A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection. In: Proceedings of the International Workshop on Quality of Multimedia Experience (QoMEX); 18 September 2009; San Diego, CA, USA. pp. 87–91. doi: 10.1109/QOMEX.2009.5246982

2. Kang L, Ye P, Li Y, et al. Convolutional neural networks for no-reference image quality assessment. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 23–28 June 2014; Columbus, OH, USA. pp. 1733–1740.

3. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016; 38(9): 1777–1787.

4. Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing. 2004; 13(4): 600–612. doi: 10.1109/TIP.2003.819861

5. Wang Z, Simoncelli EP, Bovik AC. Multiscale structural similarity for image quality assessment. The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers. 2003; 2: 1398–1402. doi: 10.1109/ACSSC.2003.1292216

6. Zhang L, Zhang L, Mou X, Zhang D. Fsim: A feature similarity index for image quality assessment. IEEE Transactions on Image Processing. 2011; 20(8): 2378–2386. doi: 10.1109/TIP.2011.2109730

7. Mittal A, Moorthy AK, Bovik AC. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing. 2012; 21(12): 4695–4708. doi: 10.1109/TIP.2012.2214050

8. Moorthy AK, Bovik AC. A two-step framework for blind image quality assessment. IEEE Transactions on Image Processing. 2010; 20(9): 2463–2474. doi: 10.1109/TIP.2011.2123162

9. Saad MA, Bovik AC, Charrier C. Blind image quality assessment: A naturalscene statistics approach in the dct domain. IEEE Transactions on Image Processing. 2012; 21(8): 3339–3352. doi: 10.1109/TIP.2012.2191563

10. Allaert B, Mennesson J, Bilasco IM, et al. Impact of the face registration techniques on facial expressions recognition. Signal Processing: Image Communication. 2018; 61: 44–53. 11. Nawaz T, Poiesi F, Cavallaro A. Assessing tracking assessment measures. In: Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP); 27–30 October 2014; Paris, France. pp. 441–445.

11. Ferzli R, Karam LJ. A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB). IEEE transactions on image processing. 2009; 18(4): 717–728. 13. Craciun P, Zerubia J. Unsupervised marked point process model for boat extraction in harbors from high resolution optical remotely sensed images. In: Proceedings of the 2013 IEEE International Conference on Image Processing; 15–18 September 2013; Melbourne, Australia. pp. 4122–4125.

12. Joshi P, Prakash S. No-reference image quality assessment using contourlet transform. Multimedia Tools and Applications. 2018; 77(13): 16977–16994.

13. Bosse S, Maniry D, Müller KR, et al. Deep neural networks for no-reference and full-reference image quality assessment. IEEE Transactions on image processing. 2017; 27(1): 206–219.

14. Liu X, Van De Weijer J, Bagdanov AD. Rankiqa: Learning from rankings for no-reference image quality assessment. arXiv preprint. 2017. arXiv:1707.08347

15. Cong H, Fu L, Zhang R, et al. Image quality assessment with gradient siamese network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 18–24 June 2022; New Orleans, LA, USA. pp. 1201–1210.

16. Xu K, Liao L, Xiao J, et al. Boosting image quality assessment through efficient transformer adaptation with local feature enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 16–22 June 2024; Seattle, WA, USA. pp. 2662–2672.

17. Avanaki NJ, Ghildyal A, Barman N, et al. Lar-iqa: A lightweight, accurate, and robust no-reference image quality assessment model. arXiv preprint. 2024; 17057.

18. Liu, H., Li, Z., Liao, S., et al. TransIFC: Invariant cues-aware feature concentration learning for efficient fine-grained bird image classification. IEEE Transactions on Multimedia, 2023.

19. Yi Deng, Jun Ma, Ziyi Wu, Wanhao Wang, Hai Liu. DSR-Net: Distinct selective rollback queries for road cracks detection with detection transformer. Digital Signal Processing. 2025; 164: 105266. doi: 10.1016/j.dsp.2025.105266

20. Zhang, Y., Li, G., Lu, J., et al. UGeNet: Uncertainty-aware gaze estimation with discriminative embedding. In: Proceedings of the European Conference on Computer Vision (ECCV); 2022. pp. 253–270.

21. Li L, Wu D, Wu J, et al. Blind image quality assessment using semantics and perception. IEEE Access. 2017; 5: 24303–24312. doi: 10.1109/ACCESS.2017.2767858

22. Zhang W, Li L, Wu J, Lin W. Blind image quality assessment using a no-reference structural similarity index. IEEE Signal Processing Letters. 2018; 25(11): 1658–1662. doi: 10.1109/LSP.2018.2870778

23. Ren H, Chen D, Wang Y. RAN4IQA: restorative adversarial nets for no-reference image quality assessment. Available online: http://arxiv.org/abs/1712.05444 (accessed on 2 June 2025).

24. Bosse S, Maniry D, Wiegand T, et al. A deep neural network for image quality assessment. In: Proceedings of the IEEE international conference on image processing (ICIP); 25–28 September 2016; Phoenix, AZ, USA. pp. 3773–3777.

25. Li D, Jiang T, Jiang M. Exploiting high-level semantics for no-reference image quality assessment of realistic blur images. In: Proceedings of the 25th ACM international conference on Multimedia; 23–27 October 2017; New York, NY, USA. pp. 378–386.

26. Lin KY, Wang G. Hallucinated-IQA: No-reference image quality assessment via adversarial learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 18–23 June 2018; Salt Lake City, UT, USA. pp. 732–741.