Eyeglass Lens Contour Detection Using Pupil Alignment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for determining the individual usage position of spectacle lenses are time-consuming, inaccurate, and prone to errors due to the complexity of frame types and low contrast in image data, especially when dealing with transparent supporting discs like drilling and Nylor glasses.

Innovation Solution

A method using a spectacle frame image data set and pupil data set to accurately determine the contour points of the lens edge, employing image recognition and pattern matching to identify known properties of the frame, which enhances precision and reliability by utilizing high contrast pupils for initial alignment and accounting for transformations like translation, rotation, and scaling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual measurement methods are used to determine lens position parameters, then measurement precision can be achieved, but time consumption increases and productivity decreases

Engineering Contradiction:
Improvelens position determination accuracyVSAvoidoptical adjustment efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual mechanical measurement methods with an automated image processing system. The system captures images of the spectacle frame and support discs, then uses computer vision algorithms to automatically determine lens position parameters, eliminating the need for manual measurement tools and procedures.

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

Solution Approach 2:

The patent creates a digital copy (image) of the physical spectacle frame and support discs. By working with the image data rather than the physical objects, the system can rapidly extract geometric parameters through pattern recognition and image analysis, significantly increasing processing speed while maintaining measurement accuracy.

Inventive Principle:
Principle #26Copying

2Productivity

If automated image processing is used to determine lens position, then productivity increases, but measurement precision deteriorates due to low contrast and complex frame types

Engineering Contradiction:
Improveoptical adjustment efficiencyVSAvoidlens position determination accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies different image processing techniques to different regions of the image based on their specific characteristics. High-contrast regions (such as the support discs) are processed to determine geometric parameters, while low-contrast regions are handled using alternative methods or are used for verification, ensuring accurate measurements despite varying image quality throughout the entire image.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent introduces support discs as intermediary elements with high contrast properties. These support discs serve as reliable reference points that can be easily detected by the image processing system. The geometric parameters of the support discs are used to infer the position and orientation of the lens, providing an indirect but accurate measurement approach that overcomes the low-contrast problem of transparent frames.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If complex image processing algorithms are applied to handle transparent frames, then adaptability improves, but device complexity increases

Engineering Contradiction:
Improveframe type coverageVSAvoidimage processing system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent divides the image processing task into separate modules, each handling specific aspects of frame analysis. One module processes the support discs to determine geometric parameters, another module handles the frame structure, and a third module integrates these results to determine overall lens position. This segmentation allows complex frame types to be processed through a systematic, manageable approach without overwhelming system complexity.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3183616B1Determining user data based on image data of a selected eyeglass frame
Publication Date: 2021.07.21 RODENSTOCK GMBH
  • EP3183616B1 patent drawingFigure 1
  • EP3183616B1 patent drawingFigure 2
  • EP3183616B1 patent drawingFigure 3

AI summary

The invention relates to an improved determining of user data for the production of an eyeglass lens for a selected eyeglass frame (32) for a user (50). For this purpose, the method according to the invention comprises: providing (12) an eyeglass frame image data set of the selected eyeglass frame (32); gathering (14) user image data at least of one portion of the user's (50) head, together with at least one part of the selected eyeglass frame (32) worn by the user (50); finding the pupils of the user in the user image data, and determining a pupil data set, said pupil data set comprising the size and/or the shape and/or the relative distance between the pupils of the user; and determining (16) contour points of the rim of the eyeglass lens to be produced in the user image data, based on the eyeglass frame image data set and the pupil data set.