Izvestiya Vysshikh Uchebnykh Zavedenii. Elektronika home

Publication of the journal

The section is currently being updated

The task of reference-free image quality evaluation is crucial in digital image processing (DIP) and computer vision, especially in resource-constrained environments with a large variety of possible distortions. Accurate evaluation methods are essential for improving the quality of visual content in different applications such as medical imaging and video streaming, developing and evaluating the performance of various DIP algorithms, and for machine learning of video analytics algorithms. In this work, the application of stacking and boosting techniques to ensemble nine popular quality measures, including such as BRISQUE, NIQE and NIMA, is considered. The methodology of ensemble construction and optimization of its settings (hyperparameters) is described. The proposed approach was tested on the KonIQ-10k, LIVE Challenge and TID2013 datasets. The results have shown that the ensemble, in particular gradient boosting in the LightGBM implementation, have improved the correlation of image quality predictions with expert evaluations.

Key words: reference-free image quality evaluation, ensemble techniques, boosting, neural networks
Published in: INFORMATION-COMMUNICATION TECHNOLOGIES
Bibliography link: Bordiuzha V., Umnyashkin S. V. The ensemble of reference-free image quality measures to improve correlation with expert evaliations. Izv.vuzov. Elektronika = Proc. Univ. Electronics. 2025;30(2):229–239. (In Russ.). https://doi.org/10.24151/1561-5405-2025-30-2-229-239.

Viktor Bordiuzha
National Research University of Electronic Technology (Russia, 124498, Moscow, Zelenograd, Shokin sq., 1)

Sergey V. Umnyashkin
National Research University of Electronic Technology (Russia, 124498, Moscow, Zelenograd, Shokin sq., 1)

1. Talebi H., Milanfar P. NIMA: Neural image assessment. IEEE Trans. Image Process. 2018;27(8):3998–4011. https://doi.org/10.1109/TIP.2018.2831899
2. Russakovsky O., Deng J., Su H., Krause J., Satheesh S., Ma S. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 2015;115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
3. Li D., Jiang T., Lin W., Jiang M. Which has better visual quality: The clear blue sky or a blurry animal? IEEE Trans. Multimedia. 2019;21(5):1221–1234. https://doi.org/10.1109/TMM.2018.2875354
4. Chen C., Mo J., Hou J., Wu H., Liao L., Sun W. et al. TOPIQ: A top-down approach from semantics to distortions for image quality assessment. arXiv.org. 06.08.2023. Available at: https://arxiv.org/abs/2308.03060 (accessed: 15.01.2025). https://doi.org/10.48550/arXiv.2308.03060
5. Mittal A., Moorthy A. K., Bovik A. C. No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 2012;21(12):4695–4708. https://doi.org/10.1109/TIP.2012.2214050
6. Mittal A., Soundararajan R., Bovik A. C. Making a “completely blind” image quality analyzer. IEEE Signal Process.Lett. 2013;22(3):209–212. https://doi.org/10.1109/LSP.2012.2227726
7. Zhang W., Ma K., Yan J., Deng D., Wang Z. Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Trans. Circuits Syst. Video Technol. 2020;30(1):36–47. https://doi.org/10.1109/TCSVT.2018.2886771
8. Ying Z., Niu H., Gupta P., Mahajan D., Ghadiyaram D., Bovik A. From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA: IEEE; 2020, pp. 3575–3585. https://doi.org/10.1109/CVPR42600.2020.00363
9. Su S., Yan Q., Zhu Y., Zhang C., Ge X., Sun J., Zhang Y. Blindly assess image quality in the wild guided by a self-adaptive hyper network. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA: IEEE; 2020, pp. 3664–3673. https://doi.org/10.1109/CVPR42600.2020.00372
10. Wang J., Chan K. C. K., Loy C. C. Exploring CLIP for assessing the look and feel of images. In: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence (AAAI’23/IAAI’23/EAAI’23). Washington, DC: AAAI Press; 2023, vol. 37, pp. 2555–2563. https://doi.org/10.1609/aaai.v37i2.25353
11. Yang S., Wu T., Shi S., Lao S., Gong Y., Cao M. et al. MANIQA: Multi-dimension attention network for no-reference image quality assessment. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). New Orleans, LA: IEEE; 2022, pp. 1191–1199. https://doi.org/10.1109/CVPRW56347.2022.00126
12. Bosse S., Maniry D., Müller K.-R., Wiegand Th., Samek W. Deep neural networks for no-reference and full-reference image quality assessment. IEEE Trans. Image Process. 2017;27(1):206–219. https://doi.org/10.1109/TIP.2017.2760518
13. Wang Z., Bovik A. C., Sheikh H. R., Simoncelli E. P. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 2004;13(4):600–612. https://doi.org/10.1109/TIP.2003.819861
14. Radford A., Kim J. W., Hallacy C., Ramesh A., Goh G., Agarwal S. et al. Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning. S. l.: PMLR, 2021; vol. 139, pp. 8748–8763. Available at: https://proceedings.mlr.press/v139/radford21a.html (accessed: 15.01.2025).
15. Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner Th. et al. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv.org. 03.06.2021. Available at: https://arxiv.org/abs/2010.11929 (accessed: 15.01.2025). https://doi.org/10.48550/arXiv.2010.11929
16. Ghadiyaram D., Bovik A. C. Massive online crowdsourced study of subjective and objective picture quality.IEEE Trans. Image Process. 2016;25(1):372–387. https://doi.org/10.1109/TIP.2015.2500021
17. Lin H., Hosu V., Saupe D. KonIQ-10k: Towards an ecologically valid and large-scale IQA database. arXiv.org. 2018. Available at: https://arxiv.org/abs/1803.08489 (accessed: 15.01.2025). https://doi.org/10.48550/arXiv.1803.08489
18. Thomee B., Shamma D. A., Friedland G., Elizalde B., Ni K., Poland D. et al. YFCC100M: The new data in multimedia research. Commun.ACM. 2016;59(2):64–73. https://doi.org/10.1145/2812802
19. Ponomarenko N., Jin L., Ieremeiev O., Lukin V., Egiazarian K., Astola J. et al. Image database TID2013: Peculiarities, results and perspectives. Signal Process. Image Commun. 2015;30:57–77. https://doi.org/10.1016/j.image.2014.10.009
20. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York: Springer; 2001. XVI, 536 p. https://doi.org/10.1007/978-0-387-21606-5
21. Scikit-learn: Machine Learning in Python. Available at: https://scikit-learn.org/stable (accessed: 16.01.2025).
22. Prokhorenkova L., Gusev G., Vorobev A., Dorogush A. V., Gulin A. CatBoost: Unbiased boosting with categorical features. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18). Red Hook, NY: Curran Associates; 2018, pp. 6639–6649.
23. Chen T., Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16). New York: ACM; 2016, pp. 785–794. https://doi.org/10.1145/2939672.2939785
24. Ke G., Meng Q., Finley Th., Wang T., Chen W., Ma W. et al. LightGBM: A highly efficient gradient boosting decision tree. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). Red Hook, NY: Curran Associates; 2017, pp. 3149–3157.
25. Li L., Jamieson K., DeSalvo G., Rostamizadeh A., Talwalkar A. Hyperband: A novel bandit-based approach to hyperparameter optimization. J. Mach. Learn. Res. 2018;18:6765–6816.
26. Optuna: An open source hyperparameter optimization framework. Availableat: https://optuna.org/ (accessed: 17.01.2025).

Information about the publication

UDK: 004.932.4
Publication type: Scientific article
DOI: 10.24151/1561-5405-2025-30-2-229-239
RISC id: EBIJVB

JATS XML