UTILIZE MACHINE LEARNING IN SELECTING HIGH QUALITY AVERAGED SEM IMAGES FROM RAW IMAGES AUTOMATICALLY

摘要

A method for evaluating images of a printed pattern is implemented by at least one programmable processor. The method includes obtaining (2310,2320) a first averaged image of the printed pattern, where the first averaged image is generated by averaging raw images of the printed pattern. The method also includes identifying (2330) one or more features of the first averaged image. The method further includes evaluating (2340) the first averaged image, by the programmable processor executing an image quality classification model and based at least on the one or more features. The evaluating includes determining (2350), by the image quality classification model, whether the first averaged image satisfies a metric.