An Interactive Personalized Garment Design Recommendation System Using Intelligent Techniques

Abstract

This paper presents a garment design recommendation system based on two mathematical models that permit the prediction and control of garment styles and structural parameters from a consumer’s personalized requirements in terms of fitting and aesthetics. Based on a formalized professional garment knowledge base, enabling the quantitative characterization of the relations between consumer profiles and garment profiles (colors, fabrics, styles, and garment fit), these two models aim at recommending the most relevant garment profile from a specific consumer profile, using reasoning with fuzzy rules and self-adjusting the garment patterns according to the feedback of the 3D virtual fitting effects corresponding to the recommended garment profile, using a genetic algorithm (GA) and support vector regression. Based on these knowledge-based models, the proposed interactive recommendation system enables the progressive optimization of the design solution through a series of human–machine interactions, i.e., the repeated execution of the cycle “design generation—virtual garment demonstration—user’s evaluation—adjustment” until the satisfaction of the end user (consumer or designer). The effectiveness of this interactive recommendation system was validated by a real case of pants customization. In a manner different from the existing approaches, the proposed system will enable designers to rapidly, accurately, intelligently, and automatically generate the optimal design solution, which is relevant in dealing with mass customization and e-shopping for fashion companies.

Keywords

• interactive recommendation
• personalized garment design
• 3D virtual garment demonstration
• fuzzy logic
• genetic algorithm
• support vector regression