此应用程序的某些内容目前无法使用。
如果这种情况持续存在,请联系我们反馈与联系
1. (WO2018140151) METHOD AND SYSTEM FOR IDENTIFYING DEFECTS OF INTEGRATED CIRCUITS
注:相关文本通过自动光符识别流程生成。凡涉及法律问题,请以 PDF 版本为准

What is claimed is:

1 . A method for identifying defects of integrated circuits, comprising:

receiving input data of a pattern associated with an integrated circuit;

determining feature data associated with features of the pattern using the input data; determining defect detection results associated with the pattern using the input data, the feature data, and defect detecti on techniques; and

determining a defect identification result using the defect detection results.

2. The method of claim 1, wherein the input data includes any of a scanning electron microscope (SEM) image associated with the pattern, a reference image associated w ith the pattern, and design data associated with a design layout of the pattern, wherein the SEM image is deter ined by a high-resolution inspection system.

3. The method of claim 2, wherein the high-resolution inspection system comprises an electron beam inspection system .

4. The method of claim 2, wherein the feature data includes any of a SEM image contour determined from the SEM image, a reference image contour determined from the reference image, a polygon associated with the pattern determined from the desi gn data, a rendered image determined from the polygon, a processed image determined from the rendered image by an image processing technique, a simulated SEM image determined based on the polygon by a SEM image simulation technique, and a simulated SEM image contour determined from the simulated SEM image.

5. The method of claim 4, wherein determining feature data associated with features of the pattern using the input data comprises:

determining auxil iary data based on the design data, wherein the design data includes graphi design system (CDS) data; and

determining the polygon from the auxi liary data, wherein a speed of determining the polygon from the auxiliary data is faster than a speed of determining the polygon from the design data.

6. The method of claim 4, wherein determining defect detection results associated with the pattern using the input data, the feature data, and defect detection techniques comprises any of:

determining whether a match exists between a first SEM image and a second SEM image, wherein the first SEM image and the second SEM image are associated with the pattern and determined by the high -resolution inspection system; and

determining whether a match exists between one of a first dataset and one of a second dataset, wherein

the first dataset includes the SEM image and the SE image contour, and the second dataset includes the polygon, the reference image, the rendered image, the processed image, the simulated SEM image, the reference image contour, and the simulated SEM image contour.

7. The method of claim 1, wherein determining a defect identification result using the defect detection results comprises:

determining the defect identification result using a learning technique that performs a weighted combination of the defect detection results.

8. The method of claim 7, wherein the learning technique comprises any of a decision tree technique and a boosting technique.

9. A system for identifying defects of integrated circuits, comprising:

a processor; and

a memory coupled to the processor, the memory configured to store a set of instructions which when executed by the processor become operational with the processor to:

receive input data of a pattern associated with an integrated circuit;

determine feature data associated with features of the pattern using the input data;

determine defect detection results associated with the pattern using the input data, the feature data, and defect detection techniques; and

determine a defect identification result using the defect detection results.

10. The system of claim 9, wherein the input data includes any of a scanning electron microscope (S M ) image associated with the pattern, a reference image associated with the pattern, and desi gn data associated with a design layout of the pattern, wherein the SEM image is determined by a high-resolution inspection system.

1 1 . The system of claim 10, wherein the high-resolution inspection system comprises an electron beam inspection system.

12. The system of claim 10, wherein the feature data includes any of a SEM image contour determined from the SEM image, a reference image contour determined from the reference image, a polygon associated with the pattern determined from the design data, a rendered image determined from the polygon, a processed image determined from the rendered image by an image processing technique, a simulated SEM image determined based on the polygon by a SEM image simulation technique, and a simulated SEM image contour determined from the simulated SEM image.

13. The system of claim 12, wherein the set of instructions operational with the processor to determine defect detection results associated with the pattern using the input data, the feature data, and defect detection techniques comprises further instructions to:

determine whether a match exists between a first SEM image and a second SEM image, wherein the first SEM image and the second SEM image are associated with the pattern and determined by the high -resolution inspection system; and

determine whether a match exists between one of a first dataset and one of a second dataset, wherein

the first dataset includes the SEM image and the SEM image contour, and the second dataset includes the polygon, the reference image, the rendered image, the processed image, the simulated SEM image, the reference image contour, and the simulated SEM image contour.

14. The system of claim 9, wherein the set of instructions operational with the processor to determine a defect identification result comprises further instructions to:

determine the defect identification result using a learning technique that performs a weighted combination of the defect detection results.

15. The system of claim 14, wherein the learning technique comprises any of a decision tree technique and a boosting technique.

16. A non-transitory computer-readable medium storing a set of instructions which when executed by a computer system using a processor become operational with the processor for identifying defects of integrated circuits, the non-transitory com puter-readabl e medium comprising instructions to:

receive input data of a pattern associated with an i ntegrated circuit;

determine feature data associated with features of the pattern using the input data; determine defect detection results associated with the pattern using the input data, the feature data, and defect detection techniques; and

determine a defect identification result using the defect detection results.

1 7. The computer-readable medium of claim 16, wherein the input data includes any of a scanning electron microscope (SEM) image associated with the pattern, a reference image associated with the pattern, and design data associated with a design layout of the pattern, wherein the SEM image i s determined by an electron beam inspection system .

18. The com puter-readabl e medium of claim 17, wherein the feature data includes any of a SEM image contour determined from the SEM image, a reference image contour determined from the reference image, a polygon associated with the pattern determined from the design data, a rendered image determined from the polygon, a processed image determined from the rendered image by an image processing technique, a simulated SEM image determined based on the polygon by a SEM image simulation technique, and a simulated SEM image contour determined from the simulated SEM image.

19. The computer-readable medium of claim 1 8, wherein the instructions to determine defect detection results associated with the pattern using the input data, the feature data, and defect detection techniques comprises further instructions to:

determine whether a match exists between a first SEM image and a second SEM image, wherein the first SEM image and the second SEM image are associated w ith the pattern and determined by the electron beam inspection system; and

determine whether a match exists between one of a first dataset and one of a second dataset, wherein

the first dataset includes the SEM image and the SEM image contour, and the second dataset includes the polygon, the reference image, the rendered image, the processed image, the simulated SEM image, the reference image contour.

and the simulated SEM image contour.

20. The com puter-readab! e medium of claim 16, wherein the instructions to determine a defect identification result using the defect detection results comprises further instructions to: determine the defect identification result using any of a decision tree technique and a boosting technique by performing a weighted combination of the defect detection results.