An Interactive Personalized Garment Design Recommendation System Using Intelligent Techniques

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