3D Foot Shape Classification for Accurate Shoe Fit Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing shoe manufacturing methods struggle to accurately fit diverse foot shapes and sizes across different countries and regions, leading to mismatches in foot width and other dimensions, especially in online sales, and require complex size variations that increase manufacturing costs and inventory risks.

Innovation Solution

A body shape analysis device and method that classifies three-dimensional foot shape data into clusters using cosine similarity and principal component analysis, allowing for personalized shoe design based on detailed foot shape characteristics beyond just length and width, and forecasts demand for various shoe sizes and shapes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If shoe size variations are increased to accommodate diverse foot shapes and sizes, then fit accuracy is improved, but manufacturing costs and inventory complexity increase

Engineering Contradiction:
Improvefit accuracyVSAvoidinventory complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments foot shape measurement into multiple dimensional parameters (length, width, height, curvature) and categorizes feet into distinct shape types. This segmentation allows manufacturers to create targeted shoe models for specific foot shape categories rather than producing numerous size variations for all possible foot shapes, thereby improving fit accuracy while controlling inventory complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms the traditional single-dimensional shoe sizing system into a multi-dimensional classification system based on foot shape parameters. By changing the parameter set used for shoe selection from merely length-based to including width, height, and curvature parameters, the system achieves better fit accuracy without proportionally increasing inventory complexity through intelligent parameter-based categorization.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If shoe size variations are increased to accommodate diverse foot shapes and sizes, then fit accuracy is improved, but manufacturing costs increase

Engineering Contradiction:
Improvefit accuracyVSAvoidmanufacturing cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

By segmenting foot shapes into distinct categories based on measured parameters, the patent enables manufacturers to produce shoe models targeted at specific foot shape groups. This reduces the total number of shoe variations needed compared to producing all possible size combinations, thereby improving fit accuracy while lowering manufacturing costs through focused production.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by measuring and analyzing only the critical dimensional parameters necessary for foot shape classification rather than attempting to account for every possible foot variation. This selective approach achieves sufficient fit accuracy without the excessive manufacturing complexity and cost that would result from accommodating every conceivable foot shape variation.

Inventive Principle:
Principle #16Partial or excessive action

3Ease of manufacture

If traditional shoe sizing based on foot length is used, then manufacturing simplicity is maintained, but fit accuracy deteriorates due to ignoring foot width and other parameters

Engineering Contradiction:
Improvemanufacturing simplicityVSAvoidfit accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent changes the parameter set from traditional single-dimensional foot length measurement to multi-dimensional foot shape parameters including length, width, height, and curvature. This parameter expansion improves fit accuracy by capturing the true complexity of foot shape variations while maintaining manufacturing simplicity through automated measurement and classification systems that process these additional parameters efficiently.

Inventive Principle:
Principle #35Parameter changes

4Measurement precision

If three-dimensional foot shape measurement is implemented, then fit accuracy is improved, but system complexity and measurement complexity increase

Engineering Contradiction:
Improvefit accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical measurement systems with optical or imaging-based three-dimensional scanning technology. This substitution captures comprehensive foot shape data more efficiently, improving fit accuracy through detailed three-dimensional measurement while actually reducing system complexity by eliminating the need for multiple separate mechanical measurement devices and procedures.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4456019B1Body shape analysis device and body shape analysis method
Publication Date: 2026.05.06 ASICS CORP
  • EP4456019B1 patent drawingFigure 1
  • EP4456019B1 patent drawingFigure 2
  • EP4456019B1 patent drawingFigure 3

AI summary

A body shape analysis device (50), includes :a model storage unit (22) configured to store, in advance, a plurality of three-dimensional homologous models for a plurality of body shapes with a three-dimensional coordinate group indicating an anatomical feature of at least part of a body; a measurement data acquirer (20) configured to acquire, as measurement data, a three-dimensional coordinate group indicating an anatomical feature corresponding to the three-dimensional homologous model of a body shape of a measurement subject; and an evaluation determination unit (24) configured to determine, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a body shape of the measurement subject by evaluating similarity in coordinates between a three-dimensional coordinate group indicating an anatomical feature in the measurement data and a three-dimensional coordinate group indicating an anatomical feature in each of the plurality of three-dimensional homologous models.