Image-Based Disposable Article Sizing via Computer Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the appropriate size of disposable absorbent articles for individuals based on physical dimensions is challenging due to reliance on weight measurements, which can be inaccurate, and the difficulty in manually measuring physical attributes.
Innovation Solution
A computer-based method that processes images of individuals to determine their physical attributes and fit parameters, which are then applied to sizing models to recommend the appropriate disposable article size from available options.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If weight-based sizing is used to recommend disposable articles, then the sizing process is simple and quick, but the accuracy of size recommendation deteriorates because weight is a poor predictor of physical dimensions
Solution Approach 1:
The patent replaces manual measurement methods with image processing technology. A computing system captures images of the subject and uses computer vision algorithms to automatically determine physical dimensions such as waist circumference, hip width, and torso length, eliminating the need for physical tape measurements while maintaining high accuracy.
Solution Approach 2:
The patent creates a digital copy of the subject's body through image capture and processing. Instead of physically measuring the subject, the system generates a digital representation from images and extracts dimensional information from this digital copy, enabling non-contact measurement with high precision.
2Measurement precision
If manual measurement of physical dimensions is performed to improve sizing accuracy, then the precision of physical attribute detection improves, but the complexity and difficulty of the measurement process increases
Solution Approach 1:
The patent enables the subject to participate in their own measurement process by posing for an image capture. The subject positions themselves according to simple instructions, and the system automatically performs all complex image processing and dimension extraction tasks, reducing the burden on both the subject and the operator.
Solution Approach 2:
The patent replaces complex manual measurement procedures with automated image processing. The computing system automatically detects key body points, calculates distances between them, and determines physical dimensions without requiring the operator to perform manual measurements, thereby simplifying the process while maintaining accuracy.
3Measurement precision
If image processing is used to determine physical attributes, then the accuracy of dimension measurement improves, but the computational complexity and processing requirements increase
Solution Approach 1:
The patent divides the image processing task into distinct stages: image capture, preprocessing, key point detection, distance calculation, and dimension determination. Each stage handles a specific aspect of the measurement process, making the overall complex system manageable and efficient through modular processing.
Solution Approach 2:
The patent performs preliminary image preprocessing steps such as noise reduction, contrast enhancement, and orientation correction before the main measurement extraction. This preliminary preparation simplifies subsequent processing tasks and improves the accuracy of dimension determination from the captured images.
Data Source
AI summary
Systems and methods for recommending a size of disposable article to be worn by a subject are provided. An image of the subject is analyzed to determine the subject's fit parameters. The fit parameters are applied to sizing models of various disposable articles.