Real-Time Eyewear Sizing Using Face Depth and Landmarks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality systems require calibration to determine the scale of a user's face, which is burdensome and inefficient, taking away from the user experience and consuming additional resources.
Innovation Solution
The system computes a real-world scale of a user's face by combining facial landmarks with a depth map, allowing augmented reality elements to be accurately positioned without calibration, and continuously updates this scale as the user moves.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image processing techniques are used to capture and process images of objects, then image processing capability is provided, but the processed images do not represent the true size of the object and require manual measurement tools
Solution Approach 1:
The system automatically calculates real-world dimensions by integrating camera intrinsic parameters, extrinsic parameters, and image processing algorithms. The processor autonomously determines object size without requiring manual measurement tools or user intervention, making the system self-sufficient for measurement tasks.
Solution Approach 2:
The patent replaces manual mechanical measurement tools (rulers, calipers) with an optical-mechanical system comprising a camera, processor, and algorithm. The system uses camera parameters and image analysis to compute real-world dimensions, substituting physical measurement tools with a digital processing system.
2Measurement precision
If a camera is used to capture images for size measurement, then image capture capability is provided, but the images require post-processing to determine true object dimensions
Solution Approach 1:
The system performs preliminary calibration to determine camera intrinsic parameters (focal length, principal point, distortion coefficients) and stores them for future use. By pre-processing and storing calibration data, the system eliminates the need for time-consuming post-processing calibration steps when measuring objects.
Solution Approach 2:
The system uses feedback from known object dimensions (when available) to refine measurement calculations. The processor compares measured dimensions with reference dimensions and adjusts calculations accordingly, improving accuracy while reducing the need for iterative post-processing.
3Measurement precision
If manual measurement tools are used alongside image processing, then measurement capability is provided, but the complexity of the system increases
Solution Approach 1:
The camera system is designed to perform multiple functions: capturing images for visual analysis, calculating real-world dimensions, and providing measurement data. By making the camera system universal, the patent eliminates the need for separate manual measurement tools, reducing overall system complexity while maintaining measurement accuracy.
Solution Approach 2:
The patent merges the measurement function with the image capture function. The same camera and processor used for image analysis are also used for dimension measurement, combining what were previously separate functions into a unified system, thereby reducing device complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems are disclosed for performing operations comprising: receiving an image that includes a depiction of a face of a user; generating a plurality of landmarks of the face based on the received image; removing a set of interfering landmarks from the plurality of landmarks resulting in a remaining set of landmarks of the plurality of landmarks; obtaining a depth map for the face of the user; and computing a real-world scale of the face of the user based on the depth map and the remaining set of landmarks.