AI Spectacle Frame Outline Detection for Virtual Try-On

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing virtual try-on solutions for spectacles face challenges in automatically detecting and accurately scaling the spectacle frame on a wearer's face, leading to distorted virtual eyeglasses and disconnection during high head movements.

Innovation Solution

A computer-implemented method using artificial intelligence to determine the outline of a spectacle frame on a wearer's face from obtained pictures, allowing for the derivation of fitting parameters and the placement of virtual spectacles with correct scaling and orientation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual outlining of spectacle frame is performed by eye care professional, then accuracy of frame detection can be ensured, but time consumption and operational complexity increase significantly

Engineering Contradiction:

Improveframe detection accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical outlining process performed by eye care professionals with an automated computer vision system that uses machine learning algorithms to detect and outline spectacle frames in images, thereby eliminating time-consuming manual operations while maintaining detection accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the computer vision algorithm independently performs frame detection and outlining without requiring human intervention, allowing the system to automatically identify and measure frame parameters from images

Inventive Principle:

Principle #25Self-service

2Productivity

If virtual spectacles are displayed without accurate frame outline detection, then processing speed can be improved, but measurement precision and virtual try-on quality deteriorate

Engineering Contradiction:

Improveprocessing speedVSAvoidfitting parameter accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent performs preliminary automated frame outline detection and fitting parameter measurement before virtual try-on display, preparing all necessary measurements in advance through automated image analysis, which enables both high processing speed and accurate fitting parameters to be achieved simultaneously

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If automated frame detection is implemented without AI, then device complexity can be reduced, but measurement precision and reliability of frame parameter extraction decrease

Engineering Contradiction:

Improvesystem complexityVSAvoidframe parameter accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces simple automated detection methods with advanced AI-based computer vision systems that use neural networks and machine learning algorithms to accurately identify and measure frame parameters, achieving high measurement precision while maintaining manageable system complexity through software-based solutions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250199342A1Improved detection of an outline of a spectacle frame

Publication Date: 2025.06.19 ESSILOR INTERNATIONAL(COMPAGNIE GENERALE D OPTIQUE)

AI summary

A computer implemented method for measuring at least one fitting parameter of a spectacle frame on a wearer. The method includes obtaining at least one picture of the wearer wearing the spectacle frame, and determining at least an outline of the spectacle frame, so as to derive from the outline at least one fitting parameter of the spectacle frame on the wearer, the outline determination being implemented by artificial intelligence.