Method and devices for determining metrology sites
Methods for determining metrology sites for products includes detecting corresponding objects in measurement data of one or more product samples, and aligning the detected objects are aligned. The methods also include analyzing the aligned objects, and determining metrology sites based on the analysis. Devices use such methods to determine metrology sites for products.
1. A method, comprising:
using one or more machine-readable hardware storage devices which comprise instructions that are executable by one or more processing devices to perform operations comprising:
detecting a plurality of objects in measurement data obtained from one or more product samples;
aligning the plurality of detected objects; and
analyzing the plurality of aligned objects to determine metrology sites for a product.
2. The method of claim 1 , wherein the measurement data comprises at least one member selected from the group consisting of a two-dimensional image, a three-dimensional image, scanning electron microscopy measurement data, computer tomography measurement data, spectroscopic measurement data, and acoustic measurement data.
3. The method of claim 1 , wherein detecting the plurality of objects comprises a template matching process.
4. The method of claim 1 , wherein detecting the plurality of objects is based on machine learning.
5. The method of claim 4 , further comprising providing an interface for human input in a training part of the machine learning.
6. The method of claim 1 , wherein aligning the plurality of objects comprises bringing the plurality of objects into a common reference coordinate system.
7. The method of claim 1 , wherein aligning the plurality of detected objects comprises finding corresponding descriptors in the plurality of detected objects.
8. The method of claim 7 , wherein finding the descriptors is based on machine learning.
9. The method of claim 8 , further comprising providing an interface for human input in a training part of the machine learning.
10. The method of claim 1 , wherein analyzing the plurality of aligned objects comprises identifying regions of different variations between the plurality of aligned objects.
11. The method of claim 10 , wherein identifying the regions of different variations comprises analyzing at least one parameter of the plurality of objected selected form the group consisting of shape, contour, mesh, and texture.
12. The method of claim 10 , wherein identifying regions of different variations comprises performing a principal component analysis.
13. The method of claim 10 , further comprising visualizing the regions of different variations.
14. The method of claim 13 , wherein visualizing the regions comprises generating a member selected form the group consisting of a heat map and a saliency map.
15. The method of claim 10 , wherein determining the metrology sites comprises determining the metrology sites based on the regions of different variances.
16. The method of claim 1 , wherein analyzing the plurality of aligned objects comprises segmenting the plurality of aligned objects based on semantic understanding.
17. The method of claim 16 , wherein the semantic understanding is based on semantic information comprising at least one member selected from the group consisting of a functionality of an object region, a material type of an object, a geometry type of an object region, surface properties of an object region, and prior metrology information.
18. The method of claim 16 , further comprising fitting predefined elements to the plurality of segmented objects.
19. The method of claim 18 , wherein the predefined elements comprise geometric elements.
20. The method of claim 18 , wherein determining metrology sites comprises at least one member selected from the group consisting of selecting dimensions of the predefined elements and selecting dimensions between the predefined elements.
21. The method of claim 1 , wherein determining metrology sites comprises solving a constraint optimization problem.
22. The method of claim 1 , wherein determining metrology sites is based on machine learning techniques.
23. The method of claim 22 , further comprising providing an interface for human input in a training part of the machine learning.
24. The method of claim 1 , wherein prior knowledge from previous measurements is used for at least one member selected from the group consisting of detecting, aligning and analyzing.
25. The method of claim 1 , wherein a classification using a trained classifier is performed for at least one member selected from the group consisting of detecting, aligning and analyzing.
26. One or more machine-readable hardware storage devices comprising instructions that are executable by one or more processing devices to perform operations comprising:
detecting a plurality of objects in measurement data obtained from one or more product samples;
aligning the plurality of detected objects; and
analyzing the plurality of aligned objects to determine metrology sites for a product.
27. A system comprising:
one or more processing devices; and
one or more machine-readable hardware storage devices comprising instructions that are executable by the one or more processing devices to perform operations comprising:
detecting a plurality of objects in measurement data obtained from one or more product samples;
aligning the plurality of detected objects; and
analyzing the plurality of aligned objects to determine metrology sites for a product.