Analysis of Structural Similarity for Image Quality Assessment

Objective. The aim of the work is to study the shortcomings of currently widespread objective mathematical criteria based on the principle of measuring the introduced error, as well as to demonstrate the advantages of criteria that take into account the features of the human visual system.

Method. The study is based on modeling the introduction of distortions by impulse noise. The resulting image quality is assessed using the above metrics. Quality assessment metrics should be consistent with subjective assessment results for a wide range of images without requiring complex computations; they should have a simple analytical form and be applicable as optimality criteria for optimizing or selecting parameters for image processing systems, including machine learning systems.

Result. The experimental results show the weakness of traditional approaches to image quality assessment based on the use of mathematical measures that assess the error introduced by the processing algorithm.

Conclusion. These metrics are currently widespread objective criteria that can be used to measure deviations, but they correlate poorly with subjective quality indicators. Metrics that take into account the peculiarities of the human visual system allow us to evaluate image quality as a measurement of structural distortions, rather than introduced errors. Our experiments have shown that the improved metric has a non-linear but exponential dependence on the probability of pixel value distortion, and correlates much better with the subjective visual perception of the quality of the image that has been processed than the standard deviation.

1. Marias K. The Constantly Evolving Role of Medical Image Processing in Oncology: From Traditional Medical Image Processing to Imaging Biomarkers and Radiomics. Journal of Imaging, 2021;7(8):124. (In Russ)

2. Zhang J., Chen Z., Liu S. Remote Sensing Image Coding for Machines on Semantic Segmentation via Contrastive Learning. IEEE Transactions on Geoscience and Remote Sensing, 2024;62:1-13. 5645013.

3. Korzhik V.I., Krasov A.V. Digital Steganography: A Textbook. Moscow: OOO KnoRus. 2023:324 p.

4. Zemtsov A.N. Digital Steganography Methods for Copyright Protection: A Monograph. Saarbrucken: LAP Lambert, 2012:148 p.

5. Bakhrushina G. I. Scrambling Digital Images /G.I. Bakhrushina, D.S. Sinkov, A.P. Bakhrushin. Scientific Notes of TNU, 2018;9(1):636-645. (In Russ)

6. Zemtsov A.N., Tsybanov V. Yu. Scrambling Digital Images. Engineering Bulletin of the Don, 2020;6. URL: ivdon.ru/ru/magazine/archive/N6y2020/6503. (In Russ)

7. Ivanov A.V. Methods, Algorithms, and Devices for Coding and Decoding Images. St. Petersburg: Publishing and Printing Association of Higher Educational Institutions, 2019: 260 p. (In Russ)

8. Zemtsov A.N. Image representation using the Le Gall transform. Bulletin of Tomsk State University. Management, Computing and Information Science, 2018; 43: 42-48. (In Russ)

9. Park K., Chae M., Cho J.H. Image Pre-Processing Method of Machine Learning for Edge Detection with Image Signal Processor Enhancement. Micromachines, 2021;12(1):73.

10. Sychev A.S. Reference-free integral-multiplicative quality indicator of digital halftone images/A.S. Sychev, I.S. Kholopov. Digital signal processing, 2018;3:49-55 (In Russ)

11. Sai S.V. Metric of distortions of fine structures in compressed images. Computer Optics, 2018; 42(5):829-837.

12. Nonparametric algorithm for automatic classification of large-volume multivariate statistical data and its application /I.V. Zenkov, A.V. Lapko, V.A. Lapko [et al.] Computer Optics, 2021;45(2): 253-260. (In Russ)

13. Wang Z., Bovik A.C., Sheikh H.R., Simoncelli E.P. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 2004;3(4):600-612.

14. Antonenko A.S. Assessing QoS Parameters for Uninterrupted IPTV Operation. T-Comm: Telecommunications and Transport, 2020;14(10.):33-38. (In Russ)

15. Zemtsov A.N. Comparative Analysis of the Efficiency of Image Compression Methods Based on the Discrete Cosine Transform and Fractal Coding. Applied Informatics, 2011; 4(34): 90-104. (In Russ)

16. Zemtsov A.N. Protection against Unauthorized Use of Graphic Information in Social Networks. Modern Science-Intensive Technologies, 2020;7;51-56. (In Russ)

17. Jierula A., Wang S. Study on Accuracy Metrics for Evaluating the Predictions of Damage Locations in Deep Piles Using Artificial Neural Networks with Acoustic Emission Data. Applied Sciences, 2021:11(5). 2314.

18. Schmid L., Roidl M., Kirchheim A. Comparing Statistical and Machine Learning Methods for Time Series Forecasting in Data-Driven Logistics – A Simulation Study. Entropy, 2025;27(1). 25.

19. Gavrilov D.A. Hardware Implementation of Dynamic Range Compression of Digital Images on Xilinx FPGAs/D.A. Gavrilov, A.V. Pavlov, D.N. Shchelkunov. Journal of Radio Electronics, 2018;1016. (In Russ)

20. Starobinets D.Yu. Automatic selection of lossy image compression parameters based on invariant moments. in Earth remote sensing. Modern Problems of Earth Remote Sensing from Space, 2017;14(5): 26-36.

21. Zemtsov A.N. Comparative analysis of the efficiency of image compression methods based on discrete cosine transform and fractal coding. Applied Informatics, 2011;5(35):77-84. (In Russ)

22. ISO/IEC 15444-1 ITU-T Rec. T. 800, Information Technology – JPEG 2000 Image Coding System: Core Coding System, 2019:196 p. (In Russ)