Body Shape Analysis Using PCA and Clustering for Custom Garment Fit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated custom clothing systems struggle to consistently provide good fit, especially for individuals with body types different from the fit model, as they often prioritize either bust or hip measurements, leading to poor fit in alternate areas.
Innovation Solution
A computer-based method for categorizing body shapes using principal component analysis and cluster analysis to identify distinct body shape categories, combined with a shape prototyping system for designing custom-fit garments that accounts for multiple measurements, including girths, widths, depths, and angles, ensuring accurate pattern adjustments for individual body types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If automated custom clothing systems prioritize bust or hip measurements, then fit in that area is improved, but fit in alternate areas deteriorates
Solution Approach 1:
The system transforms the approach from prioritizing single critical measurements (bust or hip) to utilizing a comprehensive set of body measurements including girths, widths, depths, and angles. This parameter expansion allows the pattern-making system to account for diverse body shapes without sacrificing fit accuracy in any single area, resolving the contradiction between localized fit improvement and overall fit consistency
Solution Approach 2:
The invention segments the body measurement process into multiple independent measurement categories (girths, widths, depths, angles) rather than relying on a single dominant measurement. This segmentation allows each measurement type to contribute independently to the overall pattern design, ensuring that optimizing for one body area does not compromise fit in other areas
2Ease of manufacture
If body shape categorization is not performed, then customization process is simplified, but fit accuracy for different body types deteriorates
Solution Approach 1:
The system performs preliminary body shape categorization using principal component analysis and cluster analysis before the actual pattern-making process. This preliminary classification groups individuals into distinct body shape categories, allowing the system to select appropriate base patterns and adjustment parameters in advance, thereby maintaining both process simplicity and fit accuracy
Solution Approach 2:
The invention introduces body shape categorization as an intermediary step between raw measurement data collection and final pattern generation. This intermediary classification system translates complex multi-dimensional measurement data into discrete body shape categories, which then guide the pattern-making process, ensuring both ease of operation and manufacturing precision
Data Source
AI summary
A method for categorizing body shape is provided comprising the steps of providing a data set of body shape-defining measurements of a portion of the body of interest from a plurality of subjects' bodies, wherein the measurements define a silhouette and profile (front and side) perspectives of the portion of the body of interest; conducting a principal component (PC) analysis of the data set of measurements to calculate and generate PC scores; conducting cluster analysis using the PC scores as independent variables to produce cluster analysis results; and establishing one or more body shape categories from the cluster analysis results, thereby categorizing body shapes of the plurality of subjects. A shape prototyping system is also provided for designing a custom fit garment for an individual subject, the system being based on the method for categorizing body shape.