Distance histogram for nearest neighbor defect classification
AssigneeKLA-Tencor Corporation
InventorTong Huang
Life of this patent
Estimating the term…
Abstract
A method for constructing a distance histogram for nearest neighbor classification. A training sample is determined for each of two classes. For each defect, a distance is measured in the feature space between the defect and the training sample for each of the classes. All of the distances for a given defect are normalized by dividing each distance for the given defect by the sum of all of the distances for the given defect. A histogram is constructed by plotting a chart of the normalized distances versus the number of defects having the distances. A threshold bar is placed on the center of the histogram to construct a normal nearest neighbor classifier. The threshold bar can be adjusted to the left or to the right to construct a weighted nearest neighbor classifier.
Claims3
A method for constructing a distance histogram for a nearest neighbor classification by distances in feature space between defects and training sample defects, the method comprising the steps of:
- defining a feature space,
- determining a training sample defect for each of two classes,
- for each of defects, measuring a distance in the feature space between the defect and the training sample defect for each of the two classes,
- normalizing all of the distances for a given defect by dividing each distance for the given defect by the sum of all of the distances for the given defect, and
- creating a histogram by plotting a chart with the normalized distances versus the number of defects having the distances,
- placing a threshold bar at the center of the histogram to construct a normal nearest neighbor classifier.
Dependencies are inferred from the claim text.