Defect examination on a semiconductor specimen

A computerized method of runtime defect examination on a semiconductor specimen, the method performed by a processing and memory circuitry (PMC), the method comprising:

• obtaining a first image representative of at least part of the semiconductor specimen, wherein the first image is acquired by an examination tool configured with a first focus plane;
• estimating, using a machine learning (ML) model, whether the first image is in focus, wherein the ML model is previously trained for classifying images into focused images and defocused images;
• upon an estimation that the first image is out of focus, performing focus calibration on the examination tool so as to select a second focus plane associated with an optimal focus score;
• and
• obtaining a second image acquired by the examination tool configured with the second focus plane, and estimating, using the ML model, whether the second image is in focus, wherein the second image, upon being estimated as being in focus, is used for defect examination on the semiconductor specimen.

A non-transitory computer readable storage medium tangibly embodying a program of instructions that, when executed by a computer, cause the computer to perform a method of runtime defect examination on a semiconductor specimen, the method comprising:

• obtaining a first image representative of at least part of the semiconductor specimen, wherein the first image is acquired by an examination tool configured with a first focus plane;
• estimating, using a machine learning (ML) model, whether the first image is in focus, wherein the ML model is previously trained for classifying images into focused images and defocused images;
• upon an estimation that the first image is out of focus, performing focus calibration on the examination tool so as to select a second focus plane associated with an optimal focus score;
• and
• obtaining a second image acquired by the examination tool configured with the second focus plane, and estimating, using the ML model, whether the second image is in focus, wherein the second image, upon being estimated as being in focus, is used for defect examination on the semiconductor specimen.