Charged particle image inspection

A non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of a computing device to cause the computing device to perform a method of defect classification, the method comprising:

• obtaining an inspection image of a wafer resulting from a lithography manufacturing process;
• obtaining layout data associated with the inspection image;
• obtaining a probability map derived from the layout data wherein the probability map identifies a probability of a first type of defect resulting from the lithography manufacturing process occurring in a region of the layout data;
• identifying a potential defect resulting from the lithography manufacturing process in the inspection image occurring at a first location;
• evaluating a confidence score for the potential defect based on a threshold corresponding to a known defect type;
• indicating the potential defect as an unknown defect type if the confidence score does not satisfy the threshold;
• and
• classifying the unknown defect type based on the probability map and the first location.

A method of defect classification comprising:

• obtaining an inspection image of a wafer resulting from a lithography manufacturing process;
• obtaining layout data associated with the inspection image;
• obtaining a probability map derived from the layout data, wherein the probability map identifies a probability of a first type of defect resulting from the lithography manufacturing process occurring in a region of the layout data;
• identifying a potential defect resulting from the lithography manufacturing process in the inspection image occurring at a first location;
• evaluating a confidence score for the potential defect based on a threshold corresponding to a known defect type;
• indicating the potential defect as an unknown defect type if the confidence score does not satisfy the threshold;
• and
• classifying the unknown defect type based on the probability map and the first location.