Computer-implemented method for determining a representation of a rim of a spectacles frame or a representation of the edges of the spectacle lenses

• US 10,571,721 B2
• Filed: 07/25/2019
• Issued: 02/25/2020
• Est. Priority Date: 01/27/2017
• Status: Active Grant

• Current Assignee: Carl Zeiss AG (Carl-Zeiss-Stiftung)
• Original Assignee: Carl Zeiss Vision International GMBH (Carl-Zeiss-Stiftung)
• Inventors: Nieuwenhuis, Claudia, Wojek, Christian, Schwarz, Oliver
• Primary Examiner(s): Fulton, Christopher W
• Application Number:
  US16/522,101
• Publication Number:
  US 20200018995A1
• Time in Patent Office: 215 Days
• Field of Search: 33200, 33507, 382141, 702155
• CPC Class Codes: G02B 27/0093 with means for monitoring data relating to the user, e.g. head-tracking, eye-tracking
• CPC Class Codes: G02C 13/003 Measuring during assembly or fitting of spectacles
• CPC Class Codes: G02C 13/005 Measuring geometric parameters required to locate ophtalmic lenses in spectacles frames apparatus for testing or instruments for examining the eyes per se A61B3/00; machines or devices and accessories for grinding the edges of lenses using spectacles as a template B24B9/144
• CPC Class Codes: G06F 3/012 Head tracking input arrangements
• CPC Class Codes: G06N 3/047 Probabilistic or stochastic networks
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06T 17/10 Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
• CPC Class Codes: H04N 13/282 for generating image signals corresponding to three or more geometrical viewpoints, e.g. multi-view systems

Abstract

A computer-implemented method for determining a representation of a rim of a spectacles frame or a representation of the edges of the spectacle lenses is disclosed, wherein at least two calibrated images taken from different viewing angles of a head a subject wearing the spectacles frame or the spectacles are provided, and wherein data for at least portions of the rims of the spectacles frame or the edges of the lenses are detected in each image. Further, a three-dimensional model of the spectacles frame or the spectacles is provided, based on geometric parameters, and the geometric parameters are optimised to adapt the model to the detected edges.

Claims

1. A computer-implemented method for determining a representation of a spectacle frame edge or a representation of edges of lenses of a pair of spectacles, the computer-implemented method comprising:

providing at least two images, recorded from different directions of view, of a head of a subject wearing the spectacle frame or the pair of spectacles, wherein the at least two images are calibrated with respect to one another, and wherein the calibration includes extrinsic and intrinsic properties of a camera recording the images;

determining data for at least parts of the edges of the spectacle frame or of the lenses in the at least two images to obtain detected edges;

providing a three-dimensional model, based on geometric parameters, of the spectacle frame or of the pair of spectacles; and

optimizing the geometric parameters for fitting the three-dimensional model to the detected edges.

2. The computer-implemented method as claimed in claim 1, further comprising:

optimizing parameters defining a form of the spectacle frame or pair of spectacles and an orientation of the spectacle frame or the pair of spectacles in space.

3. The computer-implemented method as claimed in claim 1, further comprising:

simultaneously recording the at least two images of the head of the subject wearing the spectacle frame or the pair of spectacles from different directions of view with at least two cameras.

4. The computer-implemented method as claimed in claim 1, wherein the at least two images contain pixels, the computer-implemented method further comprising:

mapping a value of a probability of a respective pixel containing a part of the edges of the spectacle frame or of the lenses; and

assigning the value of the probability to the respective pixel.

5. The computer-implemented method as claimed in claim 4, further comprising:

calculating a probability map mapping the probability values for a plurality of pixels with machine learning.

6. The computer-implemented method as claimed in claim 1, wherein the geometric parameters of the three-dimensional model describe straight lines approximately defining nasal and/or temporal edges of the spectacle frame of the lenses.

7. The computer-implemented method as claimed in claim 1, wherein the three-dimensional model defines each frame edge or each lens as lying approximately in a plane, or wherein the three-dimensional model is represented as lying on a surface of order n or as a linear combination of surfaces of order n.

8. The computer-implemented method as claimed in claim 7, wherein the linear combination of surfaces of order n include at least one of a plane or a paraboloid or wherein the three-dimensional model is represented by a spline.

9. The computer-implemented method as claimed in claim 1, further comprising:

generating representations of the spectacle frame or of the lenses from the three-dimensional model; and

projecting the generated representations onto a recorded image of the subject.

10. The computer-implemented method as claimed in claim 9, wherein the representations of the spectacle frame or of the lenses image prominent regions of the spectacle frame or of the lenses.

11. The computer-implemented method as claimed in claim 10, further comprising:

optimizing the geometric parameters with a cost function.

12. The computer-implemented method as claimed in claim 11, wherein the cost function assesses a correspondence of the representations projected onto the recorded images.

13. The computer-implemented method as claimed in claim 12, further comprising:

optimizing a cost value ascertained by the cost function.

14. The computer-implemented method as claimed in claim 1, wherein the position of the eyes in space is determined on a basis of the at least two images with a geometric determination of position, and wherein parameters defining the position of the eyes are incorporated into the three-dimensional model.

15. The computer-implemented method as claimed in claim 1, further comprising performing at least one of:

restricting a value range of the geometric parameters;

limiting a number of geometric parameters;

prescribing assumptions, statistics, or the assumptions and the statistics in respect of the geometry of the spectacle frame or of the lenses;

or

prescribing the assumptions, the statistics, or the assumptions and the statistics in respect of facial features, frame features, or facial and frame features in the images.

16. The computer-implemented method as claimed in claim 1, wherein the three-dimensional model contains a probability distribution specifying probabilities for possible values of the geometric parameters.

17. A computer program stored on a non-transitory storage medium and having program code for carrying out the method as claimed in claim 1, when the computer program is loaded onto a computer and/or executed on the computer.

18. A method of operating an apparatus configured to carry out the computer-implemented method as claimed in claim 1, the method comprising:

illuminating an interior of the apparatus, wherein the apparatus includes a camera carrier, which partly encloses the interior,

wherein the partly enclosed interior is open to a top side, a bottom side, and a rear side of the apparatus,

wherein the camera carrier carries at least three cameras which are arranged between two free ends of the camera carrier and directed into the partly enclosed interior, and

wherein the camera carrier includes an illumination device configured to illuminate the partly enclosed interior.

19. A method for centering at least one spectacle lens in a spectacle frame, the method comprising:

determining centration parameters for the spectacle lens by ascertaining the representation of the edge of the spectacle lens or the representation of the spectacle frame edge with the method as claimed in claim 1, and

centering the at least one spectacle lens with the determined centration parameters in the spectacle frame.

20. A method for producing a pair of spectacles, comprising centering the least one spectacle lens as claimed in claim 19.

21. A method for grinding at least one spectacle lens into a spectacle frame, the method comprising:

determining centration parameters for the spectacle lens by ascertaining the representation of the edge of the spectacle lens or the representation of the spectacle frame edge with the method as claimed in claim 1; and

grinding the at least one spectacle lens for an arrangement in the spectacle frame on the basis of the determined centration parameters.

22. A method for producing a spectacle lens, comprising grinding the spectacle lens into the spectacle frame according to claim 21.

23. An apparatus for determining a representation of a spectacle frame edge or a representation of the edges of the lenses of a pair of spectacles, the apparatus comprising:

a first camera configured to record a first image from a first direction of view,

a second camera, calibrated with respect to the first camera, configured to record a second image from a second direction of view that differs from the first direction of view, wherein the calibration includes extrinsic and intrinsic properties of the first camera and of the second camera; and

a computer having a non-transitory storage medium on which a computer program is stored and a processor for executing the computer program stored on the non-transitory storage medium, the computer program having program code causing the apparatus to;

determine data in the first image and the second image for at least parts of the edges of the spectacle frame or of the edges of the lenses;

provide at least two calibrated images, recorded from different directions of view, of a head of a subject wearing the spectacle frame or the pair of spectacles,

provide a three-dimensional model, based on geometric parameters, of the spectacle frame or of the pair of spectacles; and

optimize the geometric parameters to fit the three-dimensional model to the detected edges.