Perceptual Quality Assessment of Digital Images in the Absence of Reference Information
DOI:
https://doi.org/10.33411/IJIST/1996Keywords:
Image Quality, Image Quality Assessment, Deep Learning, Convolutional Neural NetworksAbstract
Digital multimedia content experiences a variety of degradations during the process of acquisition, processing, and transmission. Automatic approaches are required to evaluate the performance of any of these processes regarding perceptual image quality assessment. Several human observers can judge an image based on its perceptual quality, and the results may then be averaged to obtain an image quality score, making it the most accurate way of assessing image quality. Because this approach requires the engagement of human resources, an automatic method based on machine learning modelling of the human visual system is necessary. Machine learning techniques may be trained in a supervised manner by providing a set of images along with their subjective quality score as ground truth. This subjective score is sometimes expressed as the Mean Opinion Score, which is the average of numerous human judgments (MOS). In this study, we have trained a deep Convolutional Neural Network (CNN) using labelled images. The study focuses on images that are naturally distorted during acquisition, processing, or transmission rather than on synthetically distorted images with discrete distortion levels. Using naturally distorted images will result in a more general-purpose image quality evaluation model can be obtained. Furthermore, collecting a significant number of labelled images for image quality is an expensive task, and no dataset with a sufficient number of images is available, thus several ways for training the CNN will be investigated. The trained model was evaluated by determining the correlation between the ground truth (MOS) and predicted quality scores, resulting in PLCC and SROCC values of 0.7729 and 0.7489, respectively of 0.7729 & 0.7489, respectively. However, when tested on the BIQ2021 dataset, the PLCC and SROCC values were 0.7845 and 0.7588, respectively.
References
Y. Liu, H. Yu, B. Huang, G. Yue, and B. Song, “Blind Omnidirectional Image Quality Assessment Based on Structure and Natural Features,” IEEE Trans. Instrum. Meas., vol. 70, 2021, doi: 10.1109/TIM.2021.3102691.
M. Vlachos and D. Skarlatos, “Self-Adaptive Colour Calibration of Deep Underwater Images Using FNN and SfM-MVS-Generated Depth Maps,” Remote Sens. 2024, Vol. 16, Page 1279, vol. 16, no. 7, p. 1279, Apr. 2024, doi: 10.3390/RS16071279.
N. Ahmed, H. M. S. Asif, and H. Khalid, “PIQI: perceptual image quality index based on ensemble of Gaussian process regression,” Multimed. Tools Appl. 2021 8010, vol. 80, no. 10, pp. 15677–15700, Feb. 2021, doi: 10.1007/S11042-020-10286-W.
N. Ahmad, H. M. S. Asif, G. Saleem, M. U. Younus, S. Anwar, and M. R. Anjum, “Leaf Image-Based Plant Disease Identification Using Color and Texture Features,” Wirel. Pers. Commun. 2021 1212, vol. 121, no. 2, pp. 1139–1168, Aug. 2021, doi: 10.1007/S11277-021-09054-2.
L. Li, C. Mu, J. Wang, X. Liu, and N. Weng, “BVIFormer: a binocular-vision-inspired transformer with binocular competitive fusion for single-image restoration,” Sci. Reports 2026 161, vol. 16, no. 1, pp. 19862-, Apr. 2026, doi: 10.1038/s41598-026-46078-9.
J. Chen, S. Chen, L. Wee, A. Dekker, and I. Bermejo, “Deep learning based unpaired image-to-image translation applications for medical physics: a systematic review,” Phys. Med. Biol., vol. 68, no. 5, p. 05TR01, Feb. 2023, doi: 10.1088/1361-6560/ACBA74.
N. Ahmed, H. M. S. Asif, A. R. Bhatti, and A. Khan, “Deep Ensembling for Perceptual Image Quality Assessment,” Soft Comput., vol. 26, no. 16, pp. 7601–7622, May 2023, doi: 10.1007/s00500-021-06662-9.
Y. Zhang, J. Qian, D. Liu, Z. Xiao, X. Zhou, and C. Shan, “Blind Light Field Image Quality Assessment via Cross-View Encoding and Dynamic Expert Mixture,” IEEE Trans. Multimed., 2026, doi: 10.1109/TMM.2026.3715326.
X. Lv, T. Xiang, Y. Yang, and H. Liu, “Blind Dehazed Image Quality Assessment: A Deep CNN-Based Approach,” IEEE Trans. Multimed., vol. 25, pp. 9410–9424, 2023, doi: 10.1109/TMM.2023.3252267.
K. Ohashi et al., “Development of a No-Reference CT Image Quality Assessment Method Using RadImageNet Pre-trained Deep Learning Models,” J. Imaging Informatics Med. 2025 391, vol. 39, no. 1, pp. 46–58, May 2025, doi: 10.1007/S10278-025-01542-2.
K. Ma, W. Liu, K. Zhang, Z. Duanmu, Z. Wang, and W. Zuo, “End-To-end blind image quality assessment using deep neural networks,” IEEE Trans. Image Process., vol. 27, no. 3, pp. 1202–1213, 2018, doi: 10.1109/TIP.2017.2774045.
R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 586–595, Jan. 2018, doi: 10.1109/CVPR.2018.00068.
X. Ma and X. Jiang, “Multimedia image quality assessment based on deep feature extraction,” Multimed. Tools Appl. 2019 7947, vol. 79, no. 47, pp. 35209–35220, May 2019, doi: 10.1007/S11042-019-7571-Y.
N. Ahmed and H. M. S. Asif, “Perceptual quality assessment of digital images using deep features,” Comput. Informatics, vol. 39, no. 3, pp. 385–409, 2020, doi: 10.31577/CAI_2020_3_385.
J. Ma et al., “Blind Image Quality Assessment with Active Inference,” IEEE Trans. Image Process., vol. 30, pp. 3650–3663, 2021, doi: 10.1109/TIP.2021.3064195.
N. Ahmed and H. M. S. Asif, “Ensembling Convolutional Neural Networks for Perceptual Image Quality Assessment,” MACS 2019 - 13th Int. Conf. Math. Actuar. Sci. Comput. Sci. Stat. Proc., Dec. 2019, doi: 10.1109/MACS48846.2019.9024822.
Z. Yu, F. Guan, Y. Lu, X. Li, and Z. Chen, “SF-IQA: Quality and Similarity Integration for AI Generated Image Quality Assessment,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., pp. 6692–6701, 2024, doi: 10.1109/CVPRW63382.2024.00663.
V. Hosu, H. Lin, T. Sziranyi, and D. Saupe, “KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment,” IEEE Trans. Image Process., vol. 29, pp. 4041–4056, May 2020, doi: 10.1109/TIP.2020.2967829.
N. Ahmed and S. Asif, “BIQ2021: A Large-Scale Blind Image Quality Assessment Database,” J. Electron. Imaging, vol. 31, no. 05, Jan. 2023, doi: 10.1117/1.JEI.31.5.053010.
D. Varga, “No-Reference Image Quality Assessment Using the Statistics of Global and Local Image Features,” Electron. 2023, Vol. 12, Page 1615, vol. 12, no. 7, p. 1615, Mar. 2023, doi: 10.3390/ELECTRONICS12071615.
Z. Pan, F. Yuan, X. Wang, L. Xu, X. Shao, and S. Kwong, “No-Reference Image Quality Assessment via Multibranch Convolutional Neural Networks,” IEEE Trans. Artif. Intell., vol. 4, no. 1, pp. 148–160, Feb. 2023, doi: 10.1109/TAI.2022.3146804.
J. Ryu, “Improved Image Quality Assessment by Utilizing Pre-Trained Architecture Features with Unified Learning Mechanism,” Appl. Sci. 2023, Vol. 13, Page 2682, vol. 13, no. 4, p. 2682, Feb. 2023, doi: 10.3390/APP13042682.
X. Li et al., “Less is More: Learning Reference Knowledge Using No-Reference Image Quality Assessment,” Dec. 2023, Accessed: Aug. 13, 2026. [Online]. Available: https://arxiv.org/pdf/2312.00591
H. Zhang et al., “Learning degradation priors for reliable no-reference image quality assessment,” J. Vis. Commun. Image Represent., vol. 102, Jun. 2024, doi: 10.1016/j.jvcir.2024.104189.
Z. Zhou, Z. Zhou, X. Tao, H. Chen, Z. Yu, and Y. Cao, “EARNet: Error-Aware Reconstruction Network for no-reference image quality assessment,” Expert Syst. Appl., vol. 238, Mar. 2024, doi: 10.1016/j.eswa.2023.122050.
J. Ma, Y. Chen, L. Chen, and Z. Tang, “Dual-attention pyramid transformer network for No-Reference Image Quality Assessment,” Expert Syst. Appl., vol. 257, Jan. 2024, doi: 10.1016/J.ESWA.2024.125008.
Y. Zhao, Y. Zhang, T. Xia, T. Huang, X. Ben, and L. Chen, “No-reference image quality assessment based on multi-scale dynamic modulation and degradation information,” Displays, vol. 91, Jan. 2026, doi: 10.1016/J.DISPLA.2025.103207.
M. Shoaib, M. U. Younus, K. Safdar, and A. B. Dogar, “A Hybrid Approach for Efficient Database Fragmentation in Distributed Systems,” Int. J. Innov. Sci. Technol., vol. 8, no. 1, pp. 162–178, 2026, Accessed: Aug. 13, 2026. [Online]. Available: https://ideas.repec.org/a/abq/ijist1/v8y2026i1p162-178.html
Z. Zhang, “Improved Adam Optimizer for Deep Neural Networks,” 2018 IEEE/ACM 26th Int. Symp. Qual. Serv. IWQoS 2018, Jan. 2019, doi: 10.1109/IWQOS.2018.8624183.
N. Ahmed, H. M. S. Asif, and H. Khalid, “Image Quality Assessment Using a Combination of Hand-Crafted and Deep Features,” Commun. Comput. Inf. Sci., vol. 1198, pp. 593–605, 2020, doi: 10.1007/978-981-15-5232-8_51/SAVE-RESEARCH.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 50SEA

This work is licensed under a Creative Commons Attribution 4.0 International License.


















