CALCULATION OF OBJECTIVE IMAGE QUALITY INDICATORS BASED ON THE BOX-COX TRANSFORM AND THEIR CORRELATION ANALYSIS WITH VISUAL ASSESSMENT

Authors

  • Muhamediyeva D. T.

    Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University

    Author

  • Ganiyev U. N.

    Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University

    Author

Keywords:
Image quality, Box-Cox transform, entropy, sharpness, Michelson contrast, Spearman correlation, Kendall correlation, MOS, statistical moments, digital image processing.
Abstract

This paper proposes an approach based on statistical and information metrics for assessing the quality of grayscale images. In the study, image pixel intensities were normalized using the Box-Cox transform, and then their main statistical moments (mean, standard deviation, skewness, kurtosis), entropy, sharpness based on the Laplace operator, and Michelson contrast were calculated. The relationship between objective metrics and visual assessment (MOS – mean score) was analyzed using the Spearman and Kendall color correlation coefficients. Experimental results show that the proposed transform stabilizes the image intensity distribution and allows us to determine the statistical relationship between objective indicators and subjective assessment. The results of the study can be used in automatic image quality assessment systems, agricultural monitoring, and digital image processing.

References

1.Старовойтов, В. В. Цифровые изображения: от получения до обработки / В. В. Старовойтов, Ю. И. Голуб. – Минск: ОИПИ НАН Беларуси, 2014. – 202 с.

2.Голуб, Ю. И. Оценка качества цифровых изображений / Ю. И. Голуб // Системный анализ и прикладная информатика. – 2021. – № 4. – С. 4–15. https://doi.org/10.21122/2309-4923-2021-4-4-15

3.Xu, S. No-reference/blind image quality assessment: a survey / S. Xu, S. Jiang, W. Min // IETE Technical Review. – 2017. – Vol. 34, no. 3. – P. 223–245.

4.Chandler, D. M. Seven challenges in image quality assessment: past, present, and future research / D. M. Chandler // International Scholarly Research Notices. – 2013. – Т. 2013. – 53 p. https://doi.org/10.1155/2013/905685

5.Dumic, E. IQM2 – New image quality measure based on steerable pyramid wavelet transform and structural similarity index / E. Dumic, S. Grgic, M. Grgic // Signal, Image and Video Processing. – 2014. – Vol. 8, no. 6. – P. 1159–1168.

6.A multiple attributes image quality database for smartphone camera photo quality assessment / W. Zhu [et al.] // 2020 IEEE Intern. Conf. on Image Processing (ICIP). – Abu Dhabi, United Arab Emirates, 2020. – P. 2990–2994.

7.Kocić, J. Image quality parameters: A short review and applicability analysis / J. Kocić, I. Popadić, B. Livada // Proceedings of the 7th Intern. Scientific Conf. on Defensive Technologies, Belgrade. – Belgrade, 2016. – P. 391–397.

8.Голуб, Ю. И. Исследование безэталонных локальных оценок качества изображений / Ю. И. Голуб, Ф. В. Старовойтов, В. В. Старовойтов // Вестник Брестского государственного технического университета. Серия: Физика, математика, информатика. – 2019. – № 5. – С. 15–18.

9.Manap, R. A. Non-distortion-specific no-reference image quality assessment: A survey / R. A. Manap, L. Shao // Information Sciences. – 2015. – Т. 301. – P. 141–160.

10.Pertuz, S. Analysis of focus measure operators for shape-from-focus / S. Pertuz, D. Puig, M. A. Garcia // Pattern Recognition. – 2013. – Vol. 46, no. 5. – P. 1415–1432. https://doi.org/10.1016/j.patcog.2012.11.011

11.Старовойтов, В. В. Нормализация данных в машинном обучении / В. В. Старовойтов, Ю. И. Голуб // Информатика. – 2021. – Т. 18, № 1. – С. 61–71.

Downloads
Published
2026-03-06
Issue
Vol. 2 No. 3 (2026)
Section
Articles
License
Creative Commons License

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

How to Cite

CALCULATION OF OBJECTIVE IMAGE QUALITY INDICATORS BASED ON THE BOX-COX TRANSFORM AND THEIR CORRELATION ANALYSIS WITH VISUAL ASSESSMENT. (2026). Eureka Journal of Artificial Intelligence and Data Innovation, 2(3), 11-23. https://eurekaoa.com/index.php/11/article/view/565

Most read articles by the same author(s)