Deep Learning-based Adaptive Region of Interest for Measuring Critical Dimensions of Semiconductor Substrates

摘要

The measurement system is started. In one embodiment, the system includes a characterization subsystem configured to acquire one or more images of a specimen. In another embodiment, the system: receives one or more training images of a sample from a characterization subsystem; Receive one or more training region of interest (ROI) selections within the one or more training images; Generate a machine learning classifier based on the one or more training images and the one or more training ROI selections; Receive one or more product images of the sample from the characterization subsystem; Generating one or more classified regions of interest using a machine learning classifier; And a controller configured to determine one or more measurements of the specimen within the one or more classified regions of interest.