Artificial Intelligence-Based Image-to-Text Extraction and Big Data Analysisof Fashion Brand Design Archives -Focusing on the Louis Vuitton 2022–2024 Collections-

다국어 초록 (Multilingual Abstract)

This empirical study extracts brand design archives using big data analysis of designer collections, aiming to review the applicability of artificial intelligence (AI) technology in the fashion design process and related basic data. We collected collection images of Louis Vuitton from Vogue Runway for the S/S and F/W seasons of the last three years (2022, 2023, and 2024). Additionally, we used Describe Picture, an image-to-text AI generation model, to generate text descriptions for each image. Text mining techniques were then applied to derive key co-occurrence and TF-IDF words related to design elements. Network visualization and CONCOR analysis were performed using UCINET-6 to derive the brand design archive. Using Describe Picture, the research identified core features such as silhouette, color, material, pattern, and mood across each brand’s images. Big data analysis revealed that frequently extracted keywords aligned with the brands’ overarching design directions. CONCOR analysis identified four major style clusters, facilitating the derivation of a brand-specific design archive. A comparison between the Louis Vuitton archive and official Vogue Runway descriptions confirmed that the AI-derived elements accurately reflected seasonal characteristics. These findings demonstrate the potential of prompt-based generative AI as a practical tool for effectively analyzing fashion collections and supporting future design development.