Eye-Glasses Distance Estimation Using Head Tilt Morphological Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining pupillary half-distances in spectacle wearers are distorted by non-zero yaw angles, requiring complex tracking systems that are tedious to implement and prone to errors, especially when the wearer's face is not aligned with the image sensor.
Innovation Solution
A statistical method that acquires multiple images of the wearer's head at different angles, calculates morphological distances using iterative trigonometric calculations, and selects the simulated value closest to the actual eye-glasses distance by minimizing standard deviation, allowing for accurate pupillary distance estimation without the need for complex tracking systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a tracking system is used to determine the position of the spectacle frame, then measurement accuracy can be improved, but device complexity and ease of operation deteriorate due to tedious implementation and manual location requirements
Solution Approach 1:
The patent extracts the tracking system from the spectacle frame itself and replaces it with automatic image processing algorithms that analyze the spectacle frame's appearance in images. This removes the complex physical tracking hardware while maintaining the ability to determine frame position and orientation through computational methods alone.
Solution Approach 2:
The patent replaces the mechanical tracking system with an optical-digital system. Instead of using mechanical markers or sensors on the frame, the solution uses image capture and automatic computer vision algorithms to detect the spectacle frame's position, orientation, and geometric parameters, substituting mechanical complexity with computational simplicity.
2Ease of operation
If the wearer's head is not aligned with the image sensor, then ease of operation improves, but measurement precision deteriorates due to yaw angle distortion
Solution Approach 1:
The patent implements feedback by automatically detecting the wearer's head orientation (including yaw angle) from the captured images and using this information to correct the measurements. The system provides real-time feedback on the detected geometric parameters and adjusts the calculation of pupillary half-distances to compensate for any misalignment, allowing flexible positioning while maintaining accuracy.
Solution Approach 2:
The patent changes the measurement parameters dynamically based on the detected head orientation. Instead of requiring fixed alignment, the system calculates the yaw angle and other orientation parameters from the images and uses these changed parameters to adjust the measurement equations, thereby maintaining measurement precision across different head positions.
3Measurement precision
If manual location of the tracking system is required, then measurement precision can be maintained, but productivity and ease of operation deteriorate
Solution Approach 1:
The patent implements self-service by enabling the system to automatically locate and identify the spectacle frame in the captured images without any manual intervention. The computer vision algorithms automatically detect the frame's position, orientation, and geometric characteristics, eliminating the need for opticians to manually locate tracking markers and significantly improving productivity while maintaining measurement precision.
4Manufacturing precision
If multiple measurement operations are performed, then personalized optical design quality improves, but loss of time increases
Solution Approach 1:
The patent ensures continuity of useful action by capturing all necessary geometric-morphological parameters in a single integrated imaging process. Instead of performing separate measurement operations, the system continuously captures images containing information about the spectacle frame position, wearer's head orientation, and eye positions, then processes all this information together to determine all required parameters including pupillary half-distances, thereby reducing measurement time while maintaining personalized design quality.
Data Source
Figure 1~3
Figure 4
Figure 5~7
AI summary
The invention concerns a method for estimating an eye-glasses distance (VG) comprising steps of: a) acquiring at least two images of the wearer (1), on which the head (10) of the wearer has different angular positions, and b) determining, for each acquired image, a tilt angle (α301) of the head of the wearer relative to the image sensor. According to the invention, the following steps are also included: c) acquiring at least two simulated values (VG1, VG2, VG3) of the eye-glasses distance being researched, d) calculating, for each acquired image and with each simulated value, a morphological distance (EG1301, EG2301, EG3301) between the eye of the wearer and a median plane of the head of the wearer, taking said tilt angle into consideration, and e) selecting, from the simulated values, that which is closest to the eye-glasses distance of the wearer, on the basis of the head-plane distances calculated in step d).