Multimode defect detection

1 . A system configured for detecting defects on a specimen, comprising:

an inspection subsystem configured for generating first and second mode test images of a specimen with first and second modes, respectively, of the inspection subsystem; and

a computer system configured for:

calculating first and second similarity metrics for the first and second mode test images, respectively;

separating the first and second mode test images into first and second detection jobs based on the first and second similarity metrics, respectively;

generating first and second mode reference images from the first and second mode test images, respectively;

subtracting the first and second mode reference images from the first and second mode test images, respectively, to thereby generate first and second mode difference images, respectively;

combining the first and second mode test images, the first and second mode reference images, and the first and second mode difference images as an input for defect detection; and

detecting defects on the specimen based on at least the first and second mode difference images in the input, wherein said generating the first and second mode reference images, subtracting, combining, and detecting are separately performed for each of two or more of the first and second detection jobs.

2 . The system of claim 1 , wherein the computer system is further configured for aligning the first and second mode test images to each other by separately aligning the first and second mode test images to a design for the specimen.

3 . The system of claim 1 , wherein the inspection subsystem is further configured for generating the first and second mode test images by scanning a swath across a die row on the specimen with the first and second modes, respectively, wherein the swath has a length equal to or greater than a width of the die row, and wherein the computer system is further configured for performing said generating the first and second mode reference images, subtracting, combining, and detecting using only the first and second mode test images generated by the scanning.

4 . The system of claim 1 , wherein said generating the first and second mode reference images performed for at least one of the first and second detection jobs comprises selecting one or more of the first and second mode test images for said generating the first and second mode reference images, respectively, independently of positions on the specimen at which the first and second test mode images were generated.

5 . The system of claim 1 , wherein said detecting does not comprise determining first mode attributes of first mode candidate defects from only one or more of the first mode test, reference, and difference images or determining second mode attributes of second mode candidate defects from only one or more of the second mode test, reference, and difference images.

6 . The system of claim 1 , wherein said detecting comprises determining an attribute of a candidate defect based on at least one of the first mode test, reference, and difference images in combination with at least one of the second mode test, reference, and difference images.

7 . The system of claim 1 , wherein the computer system is further configured for determining an attribute of at least one of the detected defects based on at least one of the first mode test, reference, and difference images in combination with at least one of the second mode test, reference, and difference images.

8 . The system of claim 1 , wherein the computer system is further configured for detecting first mode candidate defects on the specimen based on the first mode difference images, and wherein said generating the second mode reference images, said subtracting the second mode reference images from the second mode test images, said combining, and said detecting are performed for only locations of the first mode candidate defects.

9 . The system of claim 8 , wherein detecting the first mode candidate defects comprises applying a hot threshold to the first mode difference images.

10 . The system of claim 1 , wherein at least one of the defects is only detectable in the first or second mode.

11 . The system of claim 1 , wherein said detecting comprises a one-dimensional noise cloud detection method.

12 . The system of claim 1 , wherein said detecting comprises a two-dimensional noise cloud detection method.

13 . The system of claim 1 , wherein said detecting comprises deep learning based defect detection.

14 . The system of claim 1 , wherein the computer system is further configured for performing single mode defect detection for the specimen based on only the first or second test images and for generating inspection results for the specimen based on results of the single mode defect detection and said detecting.

15 . The system of claim 1 , wherein the computer system is further configured for performing an additional multimode defect detection for the specimen based on first and second mode attributes determined for defect candidates from the first and second test images, respectively, and for generating inspection results for the specimen based on results of the additional multimode defect detection and said detecting.

16 . The system of claim 1 , wherein the inspection subsystem is further configured for generating the first and second mode test images using light.

17 . The system of claim 1 , wherein the inspection subsystem is further configured for generating the first and second mode test images using electrons.

18 . A non-transitory computer-readable medium, storing program instructions executable on a computer system for performing a computer-implemented method for detecting defects on a specimen, wherein the computer-implemented method comprises:

acquiring first and second mode test images of a specimen generated with first and second modes, respectively, of an inspection subsystem;

calculating first and second similarity metrics for the first and second mode test images, respectively;

separating the first and second mode test images into first and second detection jobs based on the first and second similarity metrics, respectively;

generating first and second mode reference images from the first and second mode test images, respectively;

subtracting the first and second mode reference images from the first and second mode test images, respectively, to thereby generate first and second mode difference images, respectively;

combining the first and second mode test images, the first and second mode reference images, and the first and second mode difference images as an input for defect detection; and

detecting defects on the specimen based on at least the first and second mode difference images, wherein said calculating, separating, generating, subtracting, combining, and detecting are performed by the computer system, and wherein said generating the first and second mode reference images, subtracting, combining, and detecting are separately performed for each of two or more of the first and second detection jobs.

19 . A computer-implemented method for detecting defects on a specimen, comprising:

acquiring first and second mode test images of a specimen generated with first and second modes, respectively, of an inspection subsystem;

calculating first and second similarity metrics for the first and second mode test images, respectively;

separating the first and second mode test images into first and second detection jobs based on the first and second similarity metrics, respectively;

generating first and second mode reference images from the first and second mode test images, respectively;

subtracting the first and second mode reference images from the first and second mode test images, respectively, to thereby generate first and second mode difference images, respectively;

combining the first and second mode test images, the first and second mode reference images, and the first and second mode difference images as an input for defect detection; and

detecting defects on the specimen based on at least the first and second mode difference images, wherein said calculating, separating, generating, subtracting, combining, and detecting are performed by a computer system, and wherein said generating the first and second mode reference images, subtracting, combining, and detecting are separately performed for each of two or more of the first and second detection jobs.