Super-resolution X-ray imaging method and apparatus

• US 10,692,184 B2
• Filed: 08/02/2018
• Issued: 06/23/2020
• Est. Priority Date: 07/05/2018
• Status: Active Grant

• Current Assignee: Bruker Nano, Inc. (Bruker Corporation)
• Original Assignee: SVXR, Inc.
• Inventors: Ratner, Edward R., Adler, David L.
• Primary Examiner(s): Artman, Thomas R
• Application Number:
  US16/053,627
• Publication Number:
  US 20200013145A1
• Time in Patent Office: 691 Days
• Field of Search: None
• CPC Class Codes: G01N 2223/42 image digitised, -enhanced in an image processor
• CPC Class Codes: G01N 2223/427 stepped imaging (selected area of sample is changed)
• CPC Class Codes: G01N 2223/645 quality control
• CPC Class Codes: G01N 23/04 and forming images of the material
• CPC Class Codes: G01N 23/18 Investigating the presence of flaws defects or foreign matter
• CPC Class Codes: G06F 18/2148 characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 3/4053 based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
• CPC Class Codes: G06T 3/4069 by subpixel displacements
• CPC Class Codes: G06T 3/4076 using the original low-resolution images to iteratively correct the high-resolution images
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06V 10/16 using multiple overlapping images; Image stitching

Abstract

The presently-disclosed technology improves the resolution of an x-ray microscope so as to obtain super-resolution x-ray images having resolutions beyond the maximum normal resolution of the x-ray microscope. Furthermore, the disclosed technology provides for the rapid generation of the super-resolution x-ray images and so enables real-time super-resolution x-ray imaging for purposes of defect detection, for example. A method of super-resolution x-ray imaging using a super-resolving patch classifier is provided. In addition, a method of training the super-resolving patch classifier is disclosed. Other embodiments, aspects and features are also disclosed.

Claims

1. A method of super-resolution x-ray imaging, the method comprising:

obtaining a set of high-resolution x-ray images of an object;

dividing each of the high-resolution x-ray images in the set into high-resolution patches;

for each patch region, inputting the high-resolution patches corresponding to the patch region to an instance of a trained super-resolving patch classifier to generate a super-resolution patch for the patch region; and

stitching together the super-resolution patches for the patch regions to obtain a super-resolution x-ray image of the object.

2. The method of claim 1, wherein the set of high-resolution x-ray images of the object are obtained by

changing an imaging condition;

acquiring a high-resolution x-ray image using the imaging condition; and

repeating the changing and acquiring steps until the set of high-resolution x-ray images is complete.

3. The method of claim 2, wherein changing the imaging condition results in a sub-pixel shift from one high-resolution x-ray image to a next high-resolution x-ray image in the set.

4. The method of claim 3, wherein the imaging condition comprises an incident angle of the x-ray beam.

5. The method of claim 4, wherein the incident angle is changed by varying a position of an x-ray source.

6. The method of claim 3, wherein the imaging condition comprises a position of an x-ray detector.

7. The method of claim 3, wherein the imaging condition comprises a position of the object.

8. The method of claim 1, wherein the super-resolving patch classifier comprises a regression classifier.

9. The method of claim 8, wherein the regression classifier comprises an artificial neural network.

10. The method of claim 8, wherein the regression classifier comprises a support vector machine.

11. The method of claim 1, further comprising:

displaying the super-resolution x-ray image on a monitor.

12. The method of claim 1, further comprising:

using the super-resolution x-ray image for detecting defects in the object.

13. The method of claim 1, wherein the super-resolution x-ray image is used for process monitoring.

14. The method of claim 1, wherein the super-resolution x-ray image has a resolution that is smaller in size than the high-resolution x-ray image by at least a factor of two.

15. An apparatus for super-resolution x-ray imaging of an object, the apparatus comprising:

an x-ray imager; and

a computer system for controlling the x-ray imager, wherein the computer system comprises a super-resolving imaging module, the super-resolution imaging module performing steps including;

obtaining a set of high-resolution x-ray images of the object;

dividing each of the high-resolution x-ray images in the set into high-resolution patches;

for each patch region, inputting the high-resolution patches corresponding to the patch region to an instance of a trained super-resolving patch classifier to generate a super-resolution patch for the patch region; and

stitching together the super-resolution patches for the patch regions to obtain a super-resolution x-ray image of the object.

16. The apparatus of claim 15, wherein the set of high-resolution x-ray images of the object are obtained by the super-resolution imaging module performing steps of:

changing an imaging condition;

acquiring a high-resolution x-ray image using the imaging condition; and

repeating the changing and acquiring steps until the set of high-resolution x-ray images is complete.

17. The apparatus of claim 16, wherein the imaging condition comprises an incident angle of the x-ray beam.

18. The apparatus of claim 17, wherein the super-resolution imaging module changes the incident angle by varying a position of an x-ray source.

19. The apparatus of claim 16, wherein the imaging condition comprises a position of an x-ray detector.

20. The apparatus of claim 16, wherein the imaging condition comprises a position of the object.

21. The apparatus of claim 15, wherein the super-resolving patch classifier comprises a regression classifier.

22. The apparatus of claim 21, wherein the regression classifier comprises an artificial neural network.

23. The apparatus of claim 21, wherein the regression classifier comprises a support vector machine.

24. The apparatus of claim 15, wherein the apparatus displays the super-resolution image on a monitor.

25. The apparatus of claim 15, wherein the apparatus comprises an inspection machine that uses the super-resolution x-ray image for detecting defects in the object.

26. The apparatus of claim 15, wherein the super-resolution x-ray image is used for process monitoring.

27. The apparatus of claim 15, wherein the super-resolution x-ray image has a resolution that is smaller in size than the high-resolution x-ray image by at least a factor of two.