IP Library Granted Patent US 12681327
Granted Patent B2
US 12681327 · App. 18/251,565 · Granted Jul 14, 2026

Determining eye-optically relevant biometrics of at least one eye from an image of an eye area

Inventors: Adam Muschielok (Munich, DE); Lukas Gromann (Freising, DE)
Assignee: Rodenstock GmbH
G02C7/027G02C7/028
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12681327
App. No.
18/251,565
Granted
Jul 14, 2026
Kind
B2
Abstract

A computer-implemented method for determining individual biometric parameters of at least one eye and to a corresponding method for manufacturing spectacle lenses, taking into account determined biometric data. The method includes providing image data comprising: at least one image of at least a part of an eye area of the user, and/or geometric information about at least a part of the eye area of the user, which results directly from at least one image of at least a part of the eye area of the user; and determining individual additional data including at least one individual biometric parameter of the at least one eye of the user, based on the image data provided, and using a statistical model describing a relation between the image data and the additional data.

Claims (40)

1 . A computer-implemented method for determining individual biometric parameters of at least one eye of a user, comprising:

providing image data comprising:

at least one image of at least a part of an eye area of the user; and/or

geometric information about at least a part of the eye area of the user, which results directly from the at least one image of the at least a part of the eye area of the user; and

determining individual additional data including at least one individual biometric parameter of the at least one eye of the user, based on the image data provided, and using a statistical model describing a relation between the image data and the additional data,

wherein the statistical model is derived or has been derived using statistical analysis of a training data set with a plurality of reference data sets, each of the reference data sets including image data and additional data assigned to the image data.

2 . The method according to claim 1 , further comprising:

providing the training data set; and

deriving the statistical model using statistical analysis of the training data set, wherein the deriving the statistical model comprises training an original model using the training data set.

3 . The method according to claim 1 , wherein the image data comprises parameters selected from a group of parameters consisting of:

one or more camera images in which the at least one eye is be seen from a front;

one or more camera images in which the at least one eye is from a side;

pupillary distance;

distance of ocular centers of rotation;

corneal diameter;

a shape and/or position of the pupil or its parts;

a shape and/or position of an outer edge of an iris or parts thereof;

three-dimensional models of an eye area;

a current direction of sight; and

presence of heterophoria and/or preferably its form/extent.

4 . The method according to claim 1 , wherein the at least one individual biometric parameter is selected from a group of parameters consisting of:

a geometric overall length of the at least one eye;

optical length of the at least one eye, integral of a refractive index along a light beam of a given wavelength, passing through a point of sharpest vision on a retina and a center of a pupil;

one or more distances of vertices of refracting surfaces of an eye to each other or to another common reference point;

a shape of the refracting surfaces which is present in a given parameterization and which is to be understood relative to a coordinate system;

a diameter or radius of a physical aperture of the eye or an optical entrance pupil which may be given for a given lighting condition;

refractive indices of optical media of the eye;

size and/or shape of a fovea;

orientation of the fovea;

position and orientation of receptors on the retina; and

size of receptive fields on the retina.

5 . The method according to claim 1 , wherein the statistical model is selected from a group of models consisting of: a linear model; a Gaussian process; a neural network; a decision tree or regression tree; a restricted Boltzmann machine; and a support vector machine.

6 . A method for manufacturing a spectacle lens, comprising:

determining individual additional data including at least one individual biometric parameter of the at least one eye of the user, based on the image data provided according to the method of claim 1 ; and

calculating the spectacle lens based on the determined individual additional data.

7 . A non-transitory computer program product which, when loaded into and executed on a memory of a computer, causes the computer to carry out a method according to claim 1 .

8 . A device for determining individual biometric parameters of the at least one eye of the user, the device comprising a calculator designed to carry out the method according to claim 1 .

9 . A device for manufacturing a spectacle lens:

a device for determining individual biometric parameters of at least one of the eyes of a user according to claim 8 ;

a lens calculator designed to calculate the spectacle lens based on the determined individual biometric parameters.