Utilize machine learning in selecting high quality averaged SEM images from raw images automatically

A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:

• obtain a first averaged image of a printed pattern, the first averaged image generated by averaging a first plurality of raw images of the printed pattern;
• identify one or more features of the first averaged image;
• and
• evaluate the first averaged image, using an image quality classification model and based at least on the one or more features, the evaluation comprising determination, by the image quality classification model, of whether the first averaged image satisfies a metric,
• wherein the image quality classification model comprises a machine learning algorithm, and
• wherein the determination of whether the first averaged image satisfies a metric is based on the machine learning algorithm.