Digital Centration System Using Facial Landmark Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for obtaining optical measurements for digital centration in eyewear, especially for online purchases, are not as accurate as in-person measurements by a qualified optician, often resulting in poor prescription fitting and higher return rates due to errors in self-measurement techniques.
Innovation Solution
A computer system using advanced computer vision and image processing technology to analyze a single photo of a wearer's face wearing glasses, detecting facial features and frame contours to estimate optical measurements such as PD, MPD, and segment heights with an average error of less than 1 mm, without requiring external objects or credit cards.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If self-measurement techniques are used for digital centration, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent replaces manual mechanical measurement methods with an automated image processing system. The computer captures images of the wearer's face and glasses, then uses algorithms to automatically detect facial landmarks, frame contours, and calculate optical measurements, eliminating the need for manual ruler-based measurement while achieving high precision.
Solution Approach 2:
The patent creates a digital copy of the physical measurement process by capturing an image of the wearer's face and glasses. This digital copy is then analyzed through image processing to extract measurement data, replacing the need for direct physical measurement while maintaining accuracy.
2Measurement precision
If specialized equipment like digital pupillometer is used, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent makes a standard camera device perform multiple functions: capturing facial features, detecting frame contours, identifying pupil positions, and calculating optical measurements. This eliminates the need for specialized equipment like digital pupillometers while achieving comparable measurement precision through software-based solutions.
Solution Approach 2:
The patent replaces specialized optical measurement equipment with a standard camera and image processing algorithms. The system uses computer vision techniques to detect facial landmarks and frame contours, substituting complex specialized hardware with a simpler, more accessible device combined with sophisticated software.
3Measurement precision
If multiple measurements are taken in a clinic, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent combines multiple measurement tasks into a single image capture and processing operation. Instead of taking separate measurements for facial features, frame positioning, and pupil locations, the system captures all necessary data in one photograph and processes it simultaneously through image analysis algorithms, dramatically reducing measurement time while maintaining precision.
Solution Approach 2:
The patent performs preliminary detection of facial landmarks and frame contours directly from the captured image before final measurement calculation. This preliminary processing prepares the data in advance, allowing rapid computation of all optical measurements without requiring multiple sequential measurement steps.
Data Source
AI summary
A method for computing centration measurements based on a digital photo, including receiving a digital photo of the face of a person wearing glasses, where the glasses have two lenses of equal size and a visible frame that surrounds each lens, where the wearer is facing the device that captured the photo, obtaining information about the frame size of the glasses, detecting facial landmarks for the face, extracting a bounding box for each of the two lenses, and computing a set of centration measurements that can be provided to a glasses manufacturer.