Abstract:
Methods and systems for generating simulated images from design information are provided. One system includes one or more computer subsystems and one or more components executed by the computer subsystem(s), which include a generative model. The generative model includes two or more encoder layers configured for determining features of design information for a specimen. The generative model also includes two or more decoder layers configured for generating one or more simulated images from the determined features. The simulated image(s) illustrate how the design information formed on the specimen appears in one or more actual images of the specimen generated by an imaging system.
Abstract:
Methods and systems for determining if a defect detected on a specimen is a DOI (Defect of Interest) or a nuisance are provided. One system includes computer subsystem(s) configured for aligning output of an inspection subsystem for an area on a specimen to simulated output of the inspection subsystem for the area on the specimen and detecting a defect in the output for the area on the specimen. The computer subsystem(s) are also configured for determining a location of the defect in the output with respect to patterned features in the simulated output based on results of the detecting and aligning, determining a distance between the determined location of the defect and a known location of interest on the specimen, and determining if the defect is a DOI or a nuisance based on the determined distance.
Abstract:
Methods and systems for generating inspection results for a specimen with an adaptive nuisance filter are provided. One method includes selecting a portion of events detected during inspection of a specimen having values for at least one feature of the events that are closer to at least one value of at least one parameter of the nuisance filter than the values for at least one feature of another portion of the events. The method also includes acquiring output of an output acquisition subsystem for the sample of events, classifying the events in the sample based on the acquired output, and determining if one or more parameters of the nuisance filter should be modified based on results of the classifying. The nuisance filter or the modified nuisance filter can then be applied to results of the inspection of the specimen to generate final inspection results for the specimen.
Abstract:
Methods and systems for integrated multi-pass reticle inspection are provided. One method for inspecting a reticle includes acquiring at least first, second, and third images for the reticle. The first image is a substantially high resolution image of light transmitted by the reticle. The second image is a substantially high resolution image of light reflected from the reticle. The third image is an image of light transmitted by the reticle that is acquired with a substantially low numerical aperture. The method also includes detecting defects on the reticle using at least the first, second, and third images for the reticle in combination.
Abstract:
Systems and methods for detecting defects on a specimen based on structural information are provided. One system includes one or more computer subsystems configured for separating the output generated by a detector of an inspection subsystem in an array area on a specimen into at least first and second segments of the output based on characteristic(s) of structure(s) in the array area such that the output in different segments has been generated in different locations in the array area in which the structure(s) having different values of the characteristic(s) are formed. The computer subsystem(s) are also configured for detecting defects on the specimen by applying one or more defect detection methods to the output based on whether the output is in the first segment or the second segment.
Abstract:
Methods and systems for detecting defects on a wafer using defect-specific information are provided. One method includes acquiring information for a target on a wafer. The target includes a pattern of interest formed on the wafer and a known DOI occurring proximate to or in the pattern of interest. The information includes an image of the target on the wafer. The method also includes searching for target candidates on the wafer or another wafer. The target candidates include the pattern of interest. The target and target candidate locations are provided to defect detection. In addition, the method includes detecting the known DOI in the target candidates by identifying potential DOI locations in images of the target candidates and applying one or more detection parameters to images of the potential DOI locations.
Abstract:
Methods and systems for detection of selected defects in relatively noisy inspection data are provided. One method includes applying a spatial filter algorithm to inspection data acquired across an area on a substrate to determine a first portion of the inspection data that has a higher probability of being a selected type of defect than a second portion of the inspection data. The selected type of defect includes a non-point defect. The inspection data is generated by combining two or more raw inspection data corresponding to substantially the same locations on the substrate. The method also includes generating a two-dimensional map illustrating the first portion of the inspection data. The method further includes searching the two-dimensional map for an event that has spatial characteristics that approximately match spatial characteristics of the selected type of defect and determining if the event corresponds to a defect having the selected type.
Abstract:
Methods and systems for setting up a classifier for defects detected on a wafer are provided. One method includes generating a template for a defect classifier for defects detected on a wafer and applying the template to a training data set. The training data set includes information for defects detected on the wafer or another wafer. The method also includes determining one or more parameters for the defect classifier based on results of the applying step.
Abstract:
Methods and systems for decision tree construction for automatic classification of defects on semiconductor wafers are provided. One method includes creating a decision tree for classification of defects detected on a wafer by altering one or more floating trees in the decision tree. The one or more floating trees are sub-trees that are manipulated as individual units. In addition, the method includes classifying the defects detected on the wafer by applying the decision tree to the defects.
Abstract:
Methods and systems for extracting comprehensive design guidance for in-line process control of wafers are provided. One method includes automatically identifying potential marginalities in a design for a device to be formed on a wafer. The method also includes automatically generating information for the potential marginalities. The automatically generated information is used to set up process control for the wafer.