Determination of contextual information for interchangeable components of an optical system

Patent metadata

Field	Value
Publication number	US-12007546-B2
Application number	US-201816610246-A
Country	US
Kind code	B2
Filing date	Apr 23, 2018
Priority date	May 5, 2017
Publication date	Jun 11, 2024
Grant date	Jun 11, 2024

Abstract

At least one image is obtained which images an external view of at least one interchangeable component (111-116) of an optical system (100). Contextual information for the at least one interchangeable component (111-116) is determined on the basis of the at least one image.

First claim

What is claimed is:

1. A method, comprising:
obtaining at least one image which depicts an external view of at least one interchangeable component of an optical system, and
determining contextual information for the at least one interchangeable component on the basis of the at least one image,
wherein the contextual information is determined using an image processing algorithm and/or a machine learning algorithm, using an artificial neural network or a support vector machine,
wherein the at least one interchangeable component comprises an interchangeable objective,
wherein the at least one image depicts a front lens of the interchangeable objective,
determining a center of the front lens in the at least one image, and
determining a contrast profile of the at least one image in a radial direction proceeding from the center of the front lens, the contrast profile indicating a change in contrast of the at least one image in the radial direction,
wherein the contextual information is determined using the contrast profile.

2. The method as claimed in claim 1 ,
wherein the machine learning algorithm is trained on the basis of reference image data which image the at least one interchangeable component under different poses and/or ambient conditions.

3. The method as claimed in claim 1 , furthermore comprising:
recognizing a machine-readable character in the at least one image,
wherein the contextual information is determined using information encoded by the machine-readable character.

4. The method as claimed in claim 1 ,
wherein the at least one image depicts the at least one interchangeable component with a predefined pose.

5. The method as claimed in claim 1 , furthermore comprising:
capturing the at least one image by means of a camera of a portable device, and
determining a pose and/or ambient condition with which the at least one image depicts the at least one interchangeable component,
wherein the contextual information is determined on the basis of the determined pose and/or the determined ambient condition.

6. The method as claimed in 1 ,
wherein the at least one interchangeable component is selected from the following group: stage insert; illumination module; analyzer stand; Wollaston (Nomarski) prism, stand; and filter insert.

7. The method as claimed in claim 1 ,
wherein determining the contextual information comprises:
determining a type of the at least one interchangeable component on the basis of the at least one image, and
accessing a database and determining an operating parameter of the at least one interchangeable component on the basis of the type of the at least one interchangeable component.

8. The method as claimed in claim 1 ,
wherein determining the contextual information comprises:
recognizing anomalies in the at least one image.

9. The method as claimed in claim 1 , furthermore comprising:
capturing the at least one image by means of a camera arranged in a stationary manner in relation to the optical system.

10. The method as claimed in claim 1 , furthermore comprising:
capturing the at least one image by means of a camera arranged in a movable manner in relation to the optical system.

11. The method as claimed in claim 10 , furthermore comprising:
capturing a measurement image by means of the camera on the basis of light which has passed through an imaging optical unit of the optical system.

12. A method, comprising:
obtaining at least one image which depicts an external view of at least one interchangeable component of an optical system, and
determining contextual information for the at least one interchangeable component on the basis of the at least one image,
wherein the contextual information is determined using an image processing algorithm and/or a machine learning algorithm, using an artificial neural network or a support vector machine,
wherein the contextual information is indicative of geometric dimensions of the at least one interchangeable component, wherein the method furthermore comprises:
on the basis of the contextual information: recognizing possible collisions between the at least one interchangeable component and a further component of the optical system.

13. A device comprising at least one processor, configured to carry out the following steps:
obtaining at least one image which depicts an external view of at least one interchangeable component of an optical system,
determining contextual information for the at least one interchangeable component on the basis of the at least one image,
wherein the contextual information is determined using an image processing algorithm and/or a machine learning algorithm, using an artificial neural network or a support vector machine,
wherein the at least one interchangeable component comprises an interchangeable objective,
wherein the at least one image depicts a front lens of the interchangeable objective—determining a center of the front lens in the at least one image, and
determining a contrast profile of the at least one image in a radial direction proceeding from the center of the front lens, the contrast profile indicating a change in contrast of the at least one image in the radial direction,
wherein the contextual information is determined using the contrast profile.

14. A device comprising at least one processor, configured to carry out the following steps:
obtaining at least one image which depicts an external view of at least one interchangeable component of an optical system, and
determining contextual information for the at least one interchangeable component on the basis of the at least one image,
wherein the contextual information is determined using an image processing algorithm and/or a machine learning algorithm, using an artificial neural network or a support vector machine,
wherein the contextual information is indicative of geometric dimensions of the at least one interchangeable component,
wherein the method furthermore comprises:
on the basis of the contextual information: recognizing possible collisions between the at least one interchangeable component and a further component of the optical system.

Assignees

• Zeiss Carl Microscopy Gmbh

Inventors

• Haase Daniel
• Ohrt Thomas

Classifications

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V20/20

  in augmented reality scenes · CPC title

• G02B21/365

  Control or image processing arrangements for digital or video microscopes (G02B21/361, G02B21/362 take precedence) · CPC title