Automated image-based process monitoring and control

摘要

Methods and devices are disclosed for automated detection of a status of wafer fabrication process based on images. The methods advantageously use segment masks to enhance the signal-to-noise ratio of the images. Metrics are then calculated for the segment mask variations in order to determine one or more combinations of segment masks and metrics that are predictive of a process non-compliance. A model can be generated as a result of the process. In another embodiment, a method uses a model to monitor a process for compliance.

主权项

1. A method for generating a model for detecting process non-compliance, comprising:
receiving a plurality of wafer images, each wafer image of the plurality of wafer images comprising a set of die images; receiving an inspection result of each die corresponding to the set of die images; generating segment masks based on the die images of each set of die images and one or more segmentation types, wherein each segment mask is configured to mask noise such that only a portion of one of the die images is shown; applying, using a processor, each segment mask to each die image to create a masked die image, and calculating a set of metrics for each masked die image; and identifying, using the processor, one or more statistically significant combinations of metric, segment mask, and wafer image, based on the die inspection results to generate a detection model.