Development of mathematical and software solutions for image comparison
Abstract
This article discusses image comparison methods, with an emphasis on traditional approaches such as the use of image hashes, color difference analysis using the ΔE metric and color histograms, as well as more complex methods, including the use of color spaces and the CIEDE2000 metric. Evaluating color differences using the CIEDE2000 formula, which takes into account human perception of color, provides more accurate information about differences between images, which is important for a number of applied tasks such as quality control of printed products, duplicate image search and visual content analysis. As part of the work, software has been developed that allows analyzing color deviations using perspective transformations and calculating the CIEDE2000 metric. The algorithm implements an effective approach to localize deviations in images, which significantly improves the accuracy and visibility of the results. With the help of heat maps, it is possible to visualize differences, which helps to identify problem areas and errors faster. The conducted research has shown that the proposed method surpasses traditional approaches in accuracy and allows for a more detailed analysis of images, especially in cases where they have been subjected to geometric distortions. Software testing was carried out using the example of various types of images such as printed products and digital copies. It can be argued that the developed program is a valuable tool in the field of image processing.
Full Text:
PDF (Russian)References
Ali N. H. M., Mahdi M. E. Detecting similarity in color images based on perceptual image hash algorithm // IOP Conference Series: Materials Science and Engineering. – IOP Publishing, 2020. – Т. 737. – № 1. – P. 012244.
Ding K. et al. Comparison of full-reference image quality models for optimization of image processing systems //International Journal of Computer Vision. – 2021. – Т. 129. – №. 4. – P. 1258–1281.
Khan M. A. et al. A smart and robust automatic inspection of printed labels using an image hashing technique // Electronics. – 2022. – Т. 11. – №. 6. – P. 955.
Thyagharajan K. K., Kalaiarasi G. A review on near-duplicate detection of images using computer vision techniques // Archives of Computational Methods in Engineering. – 2021. – Т. 28. – № 3. – P. 897–916.
Yang X. et al. Perceptual screen content image hashing using adaptive texture and shape features // IEEE Signal Processing Letters. – 2025. – P. 1–5.
Green P. Colorimetry and colour difference // Fundamentals and applications of colour engineering. – 2023. – P. 27–52.
Alkhowaiter M., Almubarak K., Zou C. Evaluating perceptual hashing algorithms in detecting image manipulation over social media platforms // 2022 IEEE International Conference on Cyber Security and Resilience (CSR). – IEEE, 2022. – P. 149–156.
Wang Z., Li T. Research on Image copyright confirmation and protection model based on blockchain //Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System. – 2021. – P. 230–234.
Liu G. H., Yang J. Y. Deep-seated features histogram: a novel image retrieval method // Pattern Recognition. – 2021. – Т. 116. – P. 107926.
Pereira A., Carvalho P., Corte-Real L. Boosting color similarity decisions using the CIEDE2000_PF Metric // Signal, Image and Video Processing. – 2022. – Т. 16. – № 7. – P. 1877–1884.
Kariper E., Cilingir A. Evaluation of color matching of three single-shade composites employing simulated 3D printed cavities with different thicknesses using CIELAB and CIEDE2000 color difference formulae // Reviews on Advanced Materials Science. – 2025. – Т. 64. – № 1. – P. 20250087.
Sharma, G., Wu, W., Dalal, E.N. The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations // Color Research and Application. – 2005. – № 30. – P. 21–30.
Tejada-Casado M. et al. Exploring the CIEDE2000 thresholds for lightness, chroma, and hue differences in dentistry //Journal of Dentistry. – 2024. – Т. 150. – P. 105327.
Bansal M., Kumar M., Kumar M. 2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors // Multimedia Tools and Applications. – 2021. – Т. 80. – № 12. – P. 18839–18857.
Bellavia F. SIFT matching by context exposed // IEEE transactions on pattern analysis and machine intelligence. – 2022. – Т. 45. – № 2. – P. 2445–2457.
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИБП для ЦОД СНЭ
ISSN: 2307-8162