Granted Patent B2

US 12,332,421 · App. 18/213,374 · Granted Jun 17, 2025

Inventors: Manuel Amthor (Jena, DE); Daniel Haase (Zoellnitz, DE); Thomas Ohrt (Golmsdorf, DE)

Assignee: Carl Zeiss Microscopy GmbH

G02B21/367G06T7/11G06T7/90G06T2207/10056

Abstract

Claims (71)

1. A computer-implemented method for color correction of microscope images, comprising:

receiving a microscope image;

localizing an object that corresponds to a predefined object type of a known color in the microscope image using an image processing program that is configured to automatically localize predefined object types of a known color;

determining a color correction on the basis of at least one image region of the localized object to bring a color of the localized object in the image region into accordance with the known color;

calculating a level of suitability for the determining of the color correction for each object localized in the microscope image;

selecting one or more of a plurality of localized objects for the determining of a color correction as a function of calculated levels of suitability; and

applying the color correction to at least a section of the microscope image or of another microscope image, or using the color correction in a capture of a further microscope image.

2. The computer-implemented method according to claim 1 ,

wherein the microscope image based on which the color correction is determined shows a microscope sample under analysis.

3. The computer-implemented method according to claim 1 ,

wherein the object used to determine the color correction is at least one of the following:

a calibration palette or marking;

a labelling field on a sample carrier;

a text on a sample carrier;

a microscope component or an illumination component; or

a sample or a sample part of a known type or a known dye for staining a sample.

4. The computer-implemented method according to claim 1 , wherein the object used to determine the color correction is located on a sample carrier, or on an insert frame of a microscope stage, or in an area visible in the microscope image behind the sample carrier.

5. The computer-implemented method according to claim 1 , wherein a possible color range is predefined for at least one of the predefined object types of known color and the color range is taken into account as a parameter during the determination of the color correction.

6. The computer-implemented method according to claim 1 , wherein the determining of the color correction occurs based on image regions of a plurality of localized objects, and wherein a contribution of a respective localized object to the determining of the color correction is weighted based on the respective level of suitability of the localized object.

7. The computer-implemented method according to claim 1 ,

wherein the level of suitability is determined based on object characteristics indicating one or more of the following:

an object size;

reflective properties or a mattness of an object surface or a material type;

a position of the object relative to an employed camera;

a color impression or purity of the object or impairments of a depiction of the object.

8. The computer-implemented method according to claim 1 , wherein the method further comprises:

determining image points within an image region of a localized object that are deemed not to belong to the object, and

ignoring these image points during the determining of the color correction.

9. The computer-implemented method according to claim 1 , further comprising

taking into account contextual information during the determining of the color correction,

wherein the contextual information relates to an illumination type, a sample type, a microscope type, employed filters or other employed optical components.

10. The computer-implemented method according to claim 1 ,

wherein the color correction is determined in the form of a region-dependent color correction to color-correct different image regions in different manners;

wherein the determining of the region-dependent color correction is based on a plurality of image regions of one or more localized objects.

11. The computer-implemented method according to claim 10 , further comprising:

dividing an image section of a localized object into at least two different image regions located at different distances from an image center; and

determining an associated color correction for each image region and combining the respectively determined color corrections in order to form the region-dependent color correction, which color-corrects an image region as a function of a distance of the image region from the image center.

12. The computer-implemented method according to claim 1 ,

wherein the applying of the color correction occurs in real time for successively captured microscope images.

13. The computer-implemented method according to claim 12 , further comprising:

checking at least some of the successively captured microscope images for changes; and

determining a new color correction whenever a change is detected.

14. A computer program, comprising commands stored on a non-transitory computer-readable medium, which, when the program is executed by a computer, causes the execution of the method according to claim 1 .

15. A microscopy system including:

a microscope for image capture; and

a computing device configured to carry out a computer-implemented method for color correction of microscope images, the method comprising:

receiving a microscope image;

localizing an object that corresponds to a predefined object type of a known color in the microscope image using an image processing program that is configured to automatically localize predefined object types of a known color;

determining a color correction on the basis of at least one image region of the localized object to bring a color of the localized object in the image region into accordance with the known color;

determining image points within an image region of a localized object that are deemed not to belong to the object;

ignoring these image points during the determining of the color correction; and

applying the color correction to at least a section of the microscope image or of another microscope image, or using the color correction in a capture of a further microscope image.

16. The microscopy system according to claim 15 , wherein the method further comprises:

calculating a level of suitability for the determining of the color correction for each object localized in the microscope image; and

selecting one or more of a plurality of localized objects for the determining of a color correction as a function of calculated levels of suitability.

17. The microscopy system according to claim 15 ,

wherein the color correction is determined in the form of a region-dependent color correction to color-correct different image regions in different manners;

wherein the determining of the region-dependent color correction is based on a plurality of image regions of one or more localized objects.

18. A computer-implemented method for color correction of microscope images, comprising:

receiving a microscope image;

localizing an object that corresponds to a predefined object type of a known color in the microscope image using an image processing program that is configured to automatically localize predefined object types of a known color;

determining a color correction on the basis of at least one image region of the localized object to bring a color of the localized object in the image region into accordance with the known color;

applying the color correction to at least a section of the microscope image or of another microscope image, or using the color correction in a capture of a further microscope image;

wherein the color correction is determined in the form of a region-dependent color correction to color-correct different image regions in different manners;

wherein the determining of the region-dependent color correction is based on a plurality of image regions of one or more localized objects.

19. The computer-implemented method according to claim 18 , further comprising:

dividing an image section of a localized object into at least two different image regions located at different distances from an image center; and

determining an associated color correction for each image region and combining the respectively determined color corrections in order to form the region-dependent color correction, which color-corrects an image region as a function of a distance of the image region from the image center.

20. The computer-implemented method according to claim 18 , wherein the method further comprises:

determining image points within an image region of a localized object that are deemed not to belong to the object, and

ignoring these image points during the determining of the color correction.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (24)