Method, apparatus, and computer program for establishing a representation of a spectacle lens edge

Patent metadata

Field	Value
Publication number	US-10564446-B2
Application number	US-201916418844-A
Country	US
Kind code	B2
Filing date	May 21, 2019
Priority date	Jan 27, 2017
Publication date	Feb 18, 2020
Grant date	Feb 18, 2020

Abstract

A computer-implemented method for establishing the representation of the edge of a spectacle lens or of a left spectacle lens and a right spectacle lens for a spectacle wearer is disclosed. The method includes: providing image data relating to the spectacle wearer with a worn spectacle frame; calculating information data derived from the image data; calculating a deterministically optimizable cost function linking the information data with spectacle lens data, wherein the spectacle lens data describe the spatial extent of at least one spectacle lens held in the spectacle frame; and setting a curve of an edge of the spectacle lens or of the left spectacle lens and the right spectacle lens by optimizing the cost function.

First claim

The invention claimed is:

1. A computer-implemented method for establishing a representation of an edge of a spectacle lens or of a left spectacle lens and a right spectacle lens for a spectacle wearer, the method comprising:
providing an image of the spectacle wearer including image data relating to the spectacle wearer with a worn spectacle frame;
providing information data concerning information of the image that are calculated from the image data of the image of the spectacle wearer;
calculating a deterministically optimizable cost function linking the information data with spectacle lens data, wherein the spectacle lens data describe a spatial extent of the spectacle lens or of the left spectacle lens and the right spectacle lens held in the spectacle frame; and
setting a curve of an edge of the spectacle lens or of the left spectacle lens and the right spectacle lens by optimizing the cost function.

2. A computer-implemented method for establishing a representation of an edge of a spectacle lens or of a left spectacle lens and a right spectacle lens for a spectacle wearer, the method comprising:
providing an image of the spectacle wearer with image data relating to the spectacle wearer with a worn spectacle frame;
providing information data concerning information of the image that are calculated from the image data of the image of the spectacle wearer;
calculating a deterministically optimizable cost function linking the information data with spectacle lens data, wherein the spectacle lens data describe a spatial extent of the spectacle lens or of the left spectacle lens and the right spectacle lens held in the spectacle frame; and
setting a curve of an edge of the spectacle lens or of the left spectacle lens and the right spectacle lens by optimizing the cost function,
wherein the calculated data concerning information of the image are at least one of data concerning a color model, data concerning an edge image, data concerning a color probability distribution, or data concerning an object in the image.

3. A computer-implemented method for establishing a representation of an edge of a spectacle lens or of a left spectacle lens and a right spectacle lens for a spectacle wearer, the method comprising:
providing an image of the spectacle wearer with image data relating to the spectacle wearer with a worn spectacle frame;
providing information data concerning information of the image that are calculated from the image data of the image of the spectacle wearer;
determining an image section of the image of the spectacle wearer from a facial feature of the spectacle wearer;
calculating a deterministically optimizable cost function linking the information data with spectacle lens data and containing a sum of convex cost function terms, wherein the spectacle lens data describe a spatial extent of at least one spectacle lens held in the spectacle frame; and
setting a curve of an edge of the spectacle lens or of the left spectacle lens and the right spectacle lens by optimizing the cost function,
wherein the information data are edge information data calculated from section image data of the image section.

4. The method according to claim 1 , wherein the information data comprise an edge information image that is established from the captured image data with an edge detection algorithm.

5. The method according to claim 4 , wherein the edge detection algorithm contains an edge detector selected from the group consisting of a gradient, a color gradient, a Canny edge detector, and a directed filter, or
wherein the edge detection algorithm accesses a filter bank with learnt edge detectors, or
wherein the edge detection algorithm is a self-learning algorithm based on machine learning.

6. The method according to claim 1 , wherein the information data comprise a color information image that is established from the captured image data by means of a color evaluation algorithm that evaluates a color of the image data.

7. The method according to claim 4 , wherein the information data comprise a color information image that is established from the captured image data with a color evaluation algorithm configured to evaluate a color of the image data.

8. The method according to claim 7 , wherein the cost function is a weighted sum of an edge detection cost term and a color evaluation cost term.

9. The method according to claim 7 , wherein calculating information data derived from the image data comprises:
establishing mirroring information data with an algorithm for identifying mirroring at the spectacle frame or at a spectacle lens received in the spectacle frame; or
establishing mirroring information data with an algorithm for identifying mirroring at the spectacle frame and at a spectacle lens received in the spectacle frame;
wherein the algorithm is configured to distinguish mirroring at the spectacle frame from mirroring at the spectacle lens.

10. The method according to claim 9 , wherein at least one of the color evaluation algorithm or the edge detection algorithm take account of the mirroring information data calculated from the image data.

11. The method according to claim 8 , wherein calculating information data derived from the image data comprises:
establishing facial feature information data with an algorithm configured to identify facial features.

12. The method according to claim 11 , wherein the color evaluation algorithm, the edge detection algorithm, or the color evaluation algorithm and the edge detection algorithm are configured to take account of the facial feature information data calculated from the image data.

13. The method according to claim 1 , wherein the cost function for establishing the edge of the left spectacle lens and the right spectacle lens for a spectacle wearer evaluates at least one of:
a symmetry of spectacle lens data; or
points in spectacle lens data, imaged onto one another with a stereo condition, to form images that correspond to different recording directions of an image capture device.

14. The method according to claim 8 , wherein calculating information data derived from the image data comprises establishing spectacle lens form information data with an algorithm configured to specify, on the basis of a spectacle lens model supplied to the algorithm or on the basis of a multiplicity of spectacle lens models supplied to the algorithm, a parametric model of a probability or a map representing probabilities about the probability that captured image data lie on a spectacle lens as spectacle lens form information data.

15. The method according to claim 8 , wherein calculating information data derived from the image data comprises establishing spectacle lens form information data with an algorithm configured to specify, on the basis of a spectacle lens model supplied to the algorithm or on the basis of a multiplicity of spectacle lens models supplied to the algorithm, a 2-D form or a 3-D form of a spectacle lens that is receivable in the spectacle frame as spectacle lens form information data.

16. The method according to claim 8 , wherein the color evaluation algorithm takes account of the spectacle lens form information data calculated from the image data.

17. The method according to claim 1 , wherein the calculated information data derived from the image data comprise a bridge center established with a bridge center detection algorithm.

18. The method according to claim 1 , wherein images recorded from at least two different directions of view form the basis of the provided image data in relation to the spect

Assignees

• Zeiss Carl Vision Int Gmbh
• Zeiss Carl Ag

Inventors

• Nieuwenhuis Claudia
• Schwarz Oliver

Classifications

• G02C13/005

  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 title

• G06T7/149

  involving deformable models, e.g. active contour models · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T7/12 Primary

  Edge-based segmentation · CPC title

• G06T2207/10012

  Stereo images · CPC title