With the growing demand for personalized clothing, the children’s apparel market is receiving significant
attention. Traditional pattern-making methods often fail to accommodate the diverse body shapes and
preferences of preschoolers, negatively impacting consumer satisfaction. Although existing studies have
examined various pattern-making techniques, they frequently overlook the unique needs of children,
resulting in limited customization options and reduced efficiency. Therefore, a comprehensive approach
is necessary to effectively integrate body size data with personalized pattern-making rules. This study
investigates a parameterized model for generating personalized children’s clothing paper patterns. It aims
to streamline the production process while catering to personalised preferences. Through the analysis
of preschooler body size data, 24 body type features are identified, leading to the development of a
discrimination model based on principal component analysis and support vector machine. This model,
integrated with clothing pattern-making rules, enhances the structure of paper patterns. Furthermore, a
parameterised paper pattern for children’s clothing is created, utilizing children’s body data to generate
tailored paper patterns efficiently. Additionally, a linkage model combining 3D and 2D aspects is
employed to evaluate clothing fit and overall effects through virtual try-on simulations. Findings suggest
reduced production complexity, time, and improved efficiency and quality in personalized pattern making.