Abstract
A method for operating a reticle inspection system includes training an analysis model of the reticle inspection system with a machine learning process, generating a difference threshold based on the machine learning process, storing a reference image, and generating a scan image of a reticle with the reticle inspection system. The method includes generating a relative difference value by comparing the scan image to the reference image. The method includes, if the relative difference value is less than the difference threshold, determining that the reticle is not defective. The method includes, if the relative difference value is greater than the difference threshold, determining that the reticle is defective.
Full Text
What is claimed is:
A method for operating a reticle inspection system includes training an analysis model of the reticle inspection system with a machine learning process, generating a difference threshold based on the machine learning process, storing a reference image, and generating a scan image of a reticle with the reticle inspection system. The method includes generating a relative difference value by comparing the scan image to the reference image. The method includes, if the relative difference value is less than the difference threshold, determining that the reticle is not defective. The method includes, if the relative difference value is greater than the difference threshold, determining that the reticle is defective.
Timeline
Filed
06/11/2026Published
10/01/2026Granted
Not AvailableIPC Codes(3)
G03F 1/84:Inspecting
G01N 21/88:Investigating the presence of flaws, defects or contamination
G01N 21/956:Inspecting patterns on the surface of objects