A conceptual model and a system for replacing text in an image while preserving the style
DOI:
https://doi.org/10.20535/SRIT.2308-8893.2025.2.04Keywords:
systems engineering method, Eriksson-Penker business profile, conceptual model, system for text replacement in images with style preservationAbstract
Text replacement in images, particularly while preserving its style, is a complex task that requires solving a range of scientific challenges and developing new technical solutions. One of the main issues is maintaining the authenticity and harmony of the image after modifications. The Research Objective is the development of a conceptual model and a system for text replacement in images with style preservation based on systems engineering methodology and the Eriksson-Penker business profile, ensuring the natural integration of new text elements into the image’s context. Implementation Methodology – the systems engineering methodology and the Eriksson-Penker business profile are used to formalize the structured process of developing a system for text replacement in images with style preservation. Research Results – a method for developing the system based on systems engineering techniques was proposed, consisting of four main stages. In the first stage, the system structure is modeled as an Eriksson-Penker business profile. In the second stage, a set of processes is defined that are characteristic of the Data Science system class and the CRISP-DM international standard. Also, the structural and dynamic representations of the conceptual model, as well as the component interaction interfaces, are modeled. The third stage involves implementing a specific version of the system, while the fourth stage focuses on system verification and validation. A systems engineering method for the conceptual model and system for text replacement in images with style preservation has been proposed. It is based on a modified Eriksson-Penker business profile for metalevel system representation and international standards for Data Science and Data Mining processes.
References
P.P. Maslianko, O.S. Maystrenko, “The system engineering of organizational system informatization projects,” KPI Sci. News, no. 6, pp. 34–42, 2008.
C. O’Neil, R. Schutt, Doing data science: Straight talk from the frontline. O’Reilly Media, Inc., 2013, 406 p.
F. Provost, T. Fawcett, Data science for business: What you need to know about data mining and data-analytic thinking. O’Reilly Media, Inc., 2013.
Pavlo P. Maslianko, Yevhenii P. Sielskyi, “Method of system engineering of neural machine translation systems,” KPI Science News, no. 2, pp. 46–55, 2021. doi: https://doi.org/10.20535/kpisn.2021.2.236939
H.-E. Eriksson, M. Penker, Business modeling with UML. New York: John Wiley & Sons, 2000, 459 p.
A. Kossiakoff, W. Sweet, S. Seymour, S. Biemer, System Engineering Principles and Practice. M.: DMK Press, 2014, 624 p.
D.K. Hitchins, Systems Engineering: A 21st Century Systems Methodology. Wiley, 2007, 528 p.
S. Krymskyi, “Metod,” in Filosofskyi Entsyklopedychnyi Slovnyk; V.I. Shynkaruk, Ed. Kyiv, Ukraine: Abrys, 2002, 742 p. doi: https://doi.org/10.20535/kpisn.2021.2.236939
Praveen Krishnan, Rama Kovvuri, Guan Pang, Boris Vassilev, Tal Hassner, “TextStyleBrush: Transfer of Text Aesthetics from a Single Example,” Journal of Latex Class Files, vol. 14, no. 8, August 2015. Available: https://arxiv.org/pdf/2106.08385
X. Huang, S. Belongie, “Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization,” 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 1510–1519. doi: https://doi.org/10.1109/ICCV.2017.167
Peter Ndajah, Hisakazu Kikuchi, Masahiro Yukawa, Hidenori Watanabe, Shogo Muramatsu, “SSIM image quality metric for denoised images,” International Conference on Visualization, Imaging and Simulation(VIS '10), pp. 53–57, 2010.
A. Horé, D. Ziou, “Image Quality Metrics: PSNR vs. SSIM,” 20th International Conference on Pattern Recognition, Istanbul, Turkey, 2010, pp. 2366–2369. doi: https://doi.org/10.1109/ICPR.2010.579
Yaniv Benny, Tomer Galanti, Sagie Benaim, Lior Wolf, “Evaluation Metrics for Conditional Image Generation,” International Journal of Computer Vision, 129, pp. 1712–1731, 2021. doi: https://doi.org/10.1007/s11263-020-01424-w
