Method and system for defect classification
Defect classification includes acquiring one or more images of a specimen, receiving a manual classification of one or more training defects based on one or more attributes of the one or more training defects, generating an ensemble learning classifier based on the received manual classification and the attributes of the one or more training defects, generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement, acquiring one or more images including one or more test defects, classifying the one or more test defects with the generated ensemble learning classifier, calculating a confidence level for each of the one or more test defects with the generated ensemble learning classifier and reporting one or more test defects having a confidence level below the generated confidence threshold via the user interface device for manual classification.
1. A method for defect classification comprising:
acquiring one or more images of a specimen, the one or more images including a plurality of defect types;
receiving a signal from a user interface device indicative of a manual classification of one or more training defects of the specimen based on one or more attributes of the one or more training defects;
generating an ensemble learning classifier based on the received manual classification and the attributes of the one or more training defects;
generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement;
acquiring one or more images including one or more test defects;
classifying the one or more test defects with the generated ensemble learning classifier;
calculating a confidence level for each of the one or more test defects with the generated ensemble learning classifier; and
reporting one or more test defects having a confidence level below the generated confidence threshold via the user interface device for manual classification.
2. The method of claim 1 , wherein the one or more training defects and the one or more test defects are disposed on the same specimen.
3. The method of claim 1 , wherein the one or more training defects and the one or more test defects are disposed on a different specimen.
4. The method of claim 1 , wherein the confidence level is calculated with a voting scheme.
5. The method of claim 1 , wherein the one or more training defects are manually classified with a real-time automatic defect classification (RT-ADC) scheme applied to the one or more attributes.
6. The method of claim 1 , wherein the ensemble learning classifier comprises:
a random forest classifier.
7. The method of claim 1 , wherein the ensemble learning classifier comprises:
a support vector machine (SVM).
8. The method of claim 1 , wherein the generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement comprises:
generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement via a cross-validation procedure.
9. An apparatus for defect classification comprising:
an inspection tool, the inspection tool including one or more detectors configured to acquire one or more images of at least a portion of a specimen;
a user interface device;
a controller, the controller including one or more processors communicatively coupled to the one or more detectors of the inspection tool, wherein the one or more processors are configured to execute a set of program instructions stored in memory, the set of program instructions configured to cause the one or more processors to:
receive the one or more images from the one or more detectors of the inspection tool;
receive a signal from a user interface device indicative of a manual classification of one or more training defects of the specimen based on one or more attributes of the one or more training defects;
generate an ensemble learning classifier based on the received manual classification and the attributes of the one or more training defects;
generate a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement;
acquire one or more images including one or more test defects;
classify the one or more test defects with the generated ensemble learning classifier;
calculate a confidence level for each of the one or more test defects with the generated ensemble learning classifier; and
report one or more test defects having a confidence level below the generated confidence threshold via the user interface device for manual classification.
10. The apparatus of claim 9 , wherein the ensemble learning classifier comprises:
a random forest classifier.
11. The apparatus of claim 9 , wherein the inspection tool comprises:
an electron beam defect review tool.
12. The apparatus of claim 9 , wherein the inspection tool comprises:
a darkfield inspection tool.
13. The apparatus of claim 9 , wherein the inspection tool comprises:
a brightfield inspection tool.