The explosive growth of generative AI technologies has fundamentally transformed brand identity creation, shifting from expensive manual design processes to scalable, automated systems accessible to startups and SMEs. This systematic literature review synthesizes 35 peer-reviewed studies from 2019-2026, mapping the evolution of AI-driven branding across four critical domains: logo generation, color palette automation, brand personality modeling, and integrated platform development. Findings reveal remarkable technical progress in individual components—GAN-based logo generators achieving human-competitive quality, SLO-PaletteGAN color systems with 1.97 inter-theme differentiation, and multi-view learning frameworks predicting brand personality with 92% accuracy. However, comprehensive integration remains elusive, with existing platforms fragmented across capabilities and lacking validated strategic alignment. Evaluation gaps persist, including small sample sizes (n<50), Western-centric training data, and insufficient cross-cultural validation. Current commercial tools (Looka, LogoAI) excel in speed but compromise on typographic precision and cultural adaptation. The review identifies five priority research directions: vector-native generation, cultural localization, business-outcome validation, human-AI collaboration patterns, and standardized evaluation frameworks. These gaps represent significant opportunities for next-generation automated branding systems capable of serving millions of global entrepreneurs while maintaining professional quality standards comparable to traditional agencies. This work establishes a unified research agenda to guide the field toward production-ready, culturally-aware comprehensive brand identity platforms.

This systematic review has comprehensively mapped the evolution of AI-driven brand identity creation systems from fragmented component generators (2019) to emerging integrated platforms (2026), synthesizing 35 peer-reviewed studies across logo generation, color palette automation, brand personality modeling, and holistic system development. The literature demonstrates remarkable technical progress—GAN-based logo generators achieving human-competitive fidelity, SLO-PaletteGAN color systems matching 96% of human harmony scores, and multi-view frameworks predicting personality traits with 92% accuracy—yet reveals persistent structural limitations that prevent production deployment.

[1]A. Ardiansyah, M. A. Rohman, and Y. A. L. Hermanto, “Perancangan Redesain Brand Identity Anamid Coffee,” JoLLA J. Lang. Literature Arts, 2022. [2]A. L. Roggeveen et al., “Forging meaningful consumer-brand relationships through creative merchandise offerings and innovative merchandising strategies,” J. Retail., 2020, doi: 10.1016/j.jretai.2020.102087. [3]F. Li, “GAN-driven color scheme generation model for brand identity design,” J. Comput. Methods Sci. Eng., 2025. [4]H. Kaur and K. Kaur, “Connecting the dots between brand logo and brand image,” Asia-Pac. J. Bus. Adm., 2019, doi: 10.1108/APJBA-10-2018-0301. [5]K. Konka, R. Saini, S. Nalla, and S. Anumulapuri, “A study on AI powered logo generation system,” World J. Adv. Res. Rev., 2025, doi: 10.30574/wjarr.2025.26.2.1804. [6]K. Osadcha and M. V. Osadcha, “GENERATIVE ARTIFICIAL INTELLIGENCE VS HUMANS IN THE PROCESS OF CREATING CORPORATE IDENTITY ELEMENTS,” Informacjn Tehnolog Zasobi Navann, 2023, doi: 10.33407/itlt.v98i6.5494. [7]K. Mohamed and F. Adiloglu, “Analyzing the Role of Gestalt Elements and Design Principles in Logo and Branding,” Int. J. Commun. Media Sci. vol. 4, no. 2, pp. 112-130, 2023. [8]M. Yu et al., “Effects of brand visual identity on consumer attitude: A Systematic Literature Review,” Environ. Social Psychol., vol. 9, no. 5, Art. no. 114234, 2024. doi: 10.37256/es.2024.9.5.123. [9]R. A. Wertz, “Brand new how visual context shapes initial response to logos and corporate visual identity systems,” J. Product Brand Manage., vol. 32, no. 3, pp. 245-263, 2023. [10]R. Dew, A. Ansari, and O. Toubia, “Letting Logos Speak Leveraging Multiview Representation Learning for Data-Driven Branding and Logo Design,” Marketing Sci., Providence, RI, USA, vol. 40, no. 5, pp. 867-888, 2021. doi: 10.1287/mksc.2021.1295. [11]S. Sayatman, B. Soewito, and N. Noordyanto, “Pengembangan Konsep Brand Identity dan Visual System ITS yang Lebih Terintegrasi,” J. Desain Idea J. Desain Produk Ind. Inst. Teknol. Sepuluh Nopember Surabaya, 2021. [12]S. H. Lee and H. R. Seo, “A Study on Developing a Bespoke Stationery Brand Logo through Generative AI Design Platforms Focusing on Adobe Firefly and ChatGPT,” Korea Inst. Des. Res. Soc., 2025. [13]T. Çelik and E. A. Ergin, “AI-driven design exploration Utilizing brand logos as an inspiration source for architectural design,” Artif. Intell. Eng. Des. Anal. Manuf., 2025. [14]U. Pamuksuz, J. T. Yun, and A. Humphreys, “A Brand-New Look at You Predicting Brand Personality in Social Media Networks with Machine Learning,” J. Interact. Marketing, 2021. [15]V. Shah and N. Das, “Brand Birth to Brand Launch the Success Story Case Study by Communication Design Students under the module – Brand Design,” Int. J. Sci. Technol., 2025. [16]Y.-H. Chen, L. Kara, and J. Cagan, “BIGNet A Deep Learning Architecture for Brand Recognition with Geometry-based Explainability,” J. Mech. Des., 2023. [17]Y. J. Hwang, “A Study on the Use of Generative Artificial Intelligence Design Platform for BI Development -Focusing on the Use of the Midjourney-,” J. Korean Soc. Des. Culture, 2023. [18]Y. Jun and H. Lee, “A sound brand identity design The interplay between sound symbolism and typography on brand attitude and memory,” J. Retail. Consum. Serv., 2022. [19]C.-H. Wu and M.-T. Chou, “An Exploratory Study of Artificial Intelligence-Generated Content AIGC and Brand Design,” Proc. 2024 8th Int. Conf. Educ. Multimedia Technol., 2024. [20]D. Elikan and Y. Pigneur, “A Visual Inquiry Tool for Brand Identity,” Proc. Hawaii Int. Conf. Syst. Sci., 2019. [21]N. Zhao et al., “ICONATE Automatic Compound Icon Generation and Ideation,” Proc. Int. Conf. Human Factors Comput. Syst., 2020. [22]P. Chi et al., “Automatic Video Creation From a Web Page,” Proc. ACM Symp. User Interface Softw. Technol., 2020. [23]R. Agrawal, S. Sivaprasad, and N. Pedanekar, “Color Me Good Branding in the Coloring Style of Movie Posters,” Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops, 2021. [24]S. Gawad and M. Kim, “BrandCrafter AI, an AI-Based Brand Identity Generation Platform,” Proc. Comput. Commun. Workshop Conf., 2025. [25]S. Mishra, M. Verma, and J. Gligorijevic, “Guiding creative design in online advertising,” Proc. ACM Conf. Recommender Syst., 2019. [26]T. Markovic et al., “Crafting Startup Brand Identity and Positioning in the Information Technology Arena,” Proc. 2024 Int. Conf. Artif. Intell. Comput. Data Sci. Appl. (ACDSA), 2024. [27]T. Zhao et al., “GUIGAN Learning to Generate GUI Designs Using Generative Adversarial Networks,” Proc. Int. Conf. Softw. Eng., 2021. [28]Y.-H. Chen, L. Kara, and J. Cagan, “Automating Style Analysis and Visualization with Explainable AI – Case Studies on Brand Recognition,” Proc. Des. Autom. Conf., 2023. [29]Z. Wu et al., “Understanding and Modeling User-Perceived Brand Personality from Mobile Application UIs,” Proc. Int. Conf. Human Factors Comput. Syst., 2019. [30]A. Manavis, K. Kakoulis, and P. Kyratsis, “A Brief Review of Computational Product Design A Brand Identity Approach,” Machines, 2023. [31]P. Pramuditha et al., “Canva Magic Menggali Perilaku Pengguna dalam Membangun Brand Identity UMKM Bandung di Era Digital,” ATRABIS J. Adm. Bisnis e-J., 2024. [32]J. Hartmann et al., “The Power of Brand Selfies in Consumer-Generated Brand Images,” Social Science Research Network, 2020.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close