# US 12,007,546 B2 · Determination of contextual information for interchangeable components of an optical system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,007,546 B2 - Document ID: US12007546B2 - Status: Granted - Kind: B2 - Application number: 16/610,246 - Filed: 2018-04-23 - Published: 2020-02-20 - Granted: 2024-06-11 - Earliest claimed: 2017-05-05 - Assignees: Carl Zeiss Microscopy GmbH - Applicants: Carl Zeiss Microscopy GmbH - Inventors: Daniel Haase; Thomas Ohrt - Web page: https://patentgrep.com/patent/US12007546B2 ## CPC - G02B 21/24: Base structure - G02B 21/362: {Mechanical details, e.g. mountings for the camera or image sensor, housings (G02B21/364 takes precedence)} - G02B 21/365: {Control or image processing arrangements for digital or video microscopes (G02B21/361, G02B21/362 take precedence)} - G06N 20/00: Machine learning - G06T 7/73: using feature-based methods - G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]} - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V 20/20: in augmented reality scenes - G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## 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. ## Claims ### Claim 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. ### Claim 2 (depends on 1) 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. ### Claim 3 (depends on 1) 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. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein the at least one image depicts the at least one interchangeable component with a predefined pose. ### Claim 5 (depends on 1) 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. ### Claim 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. ### Claim 7 (depends on 1) 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. ### Claim 8 (depends on 1) The method as claimed in claim 1, wherein determining the contextual information comprises: recognizing anomalies in the at least one image. ### Claim 9 (depends on 1) 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. ### Claim 10 (depends on 1) 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. ### Claim 11 (depends on 10) 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. ### Claim 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. ### Claim 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. ### Claim 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.