Abstract: Defect classification includes acquiring one or more images of a specimen, receiving a manual classification of one or more training defects based on one or more attributes of the one or more training defects, generating an ensemble learning classifier based on the received manual classification and the attributes of the one or more training defects, generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement, acquiring one or more images including one or more test defects, classifying the one or more test defects with the generated ensemble learning classifier, calculating a confidence level for each of the one or more test defects with the generated ensemble learning classifier and reporting one or more test defects having a confidence level below the generated confidence threshold via the user interface device for manual classification.

Abstract: Defect classification includes acquiring one or more images of a specimen, receiving a manual classification of one or more training defects based on one or more attributes of the one or more training defects, generating an ensemble learning classifier based on the received manual classification and the attributes of the one or more training defects, generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement, acquiring one or more images including one or more test defects, classifying the one or more test defects with the generated ensemble learning classifier, calculating a confidence level for each of the one or more test defects with the generated ensemble learning classifier and reporting one or more test defects having a confidence level below the generated confidence threshold via the user interface device for manual classification.

Abstract: Defect classification includes acquiring one or more images of a specimen, receiving a manual classification of one or more training defects based on one or more attributes of the one or more training defects, generating an ensemble learning classifier based on the received manual classification and the attributes of the one or more training defects, generating a confidence threshold for each defect type of the one or more training defects based on a received classification purity requirement, acquiring one or more images including one or more test defects, classifying the one or more test defects with the generated ensemble learning classifier, calculating a confidence level for each of the one or more test defects with the generated ensemble learning classifier and reporting one or more test defects having a confidence level below the generated confidence threshold via the user interface device for manual classification.

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: Various embodiments for determining parameters for wafer inspection and/or metrology are provided.

Abstract: Systems and methods for generating information for use in a wafer inspection process are provided. One method includes acquiring output of an inspection system for die(s) located on wafer(s), combining the output for the die(s) based on within die positions of the output, determining, on a within die position basis, a statistical property of variation in values of characteristic(s) of the combined output, and assigning the within die positions to different groups based on the statistical properties determined for the within die positions. The method also includes storing information for the within die positions and the different groups to which the within die positions are assigned in a storage medium that is accessible to the inspection system for performing the wafer inspection process, which includes applying defect detection parameter(s) to additional output of the inspection system generated for a wafer based on the information thereby detecting defects on the wafer.

Abstract: Systems and methods for generating information for use in a wafer inspection process are provided. One method includes acquiring output of an inspection system for die(s) located on wafer(s), combining the output for the die(s) based on within die positions of the output, determining, on a within die position basis, a statistical property of variation in values of characteristic(s) of the combined output, and assigning the within die positions to different groups based on the statistical properties determined for the within die positions. The method also includes storing information for the within die positions and the different groups to which the within die positions are assigned in a storage medium that is accessible to the inspection system for performing the wafer inspection process, which includes applying defect detection parameter(s) to additional output of the inspection system generated for a wafer based on the information thereby detecting defects on the wafer.

Abstract: Systems and methods for design-based inspection using repeating structures are provided.

Abstract: Methods and systems for determining inspection scenarios without input from a user are presented. Inspection scenarios include at least one acquisition mode, defect detection parameter values, and classification parameter values. In one example, a number of defect events are determined by a hot inspection of a wafer surface. The defect events are classified and attributes associated with each defect event are identified. The defect events are labeled with this information. Based on the identified attributes and classification, inspection scenarios are determined. The inspection scenarios are solutions in a mathematical space formed by the identified attributes. In some examples, a plurality of inspection scenarios are determined and a desired inspection scenario is selected from the plurality based on the number of defects of interest and the number of nuisance events captured by the selected inspection scenario.

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: Various embodiments for determining dynamic care areas are provided. In one embodiment, a first inspection process is performed on a wafer after a first fabrication step has been performed on the wafer and before a second fabrication process has been performed on the wafer. One embodiment includes determining care areas for a second inspection process based on inspection results generated by the first inspection process. The second inspection process will be performed on the wafer after the second fabrication step has been performed on the wafer.

Abstract: Methods and systems for determining inspection scenarios without input from a user are presented. Inspection scenarios include at least one acquisition mode, defect detection parameter values, and classification parameter values. In one example, a number of defect events are determined by a hot inspection of a wafer surface. The defect events are classified and attributes associated with each defect event are identified. The defect events are labeled with this information. Based on the identified attributes and classification, inspection scenarios are determined. The inspection scenarios are solutions in a mathematical space formed by the identified attributes. In some examples, a plurality of inspection scenarios are determined and a desired inspection scenario is selected from the plurality based on the number of defects of interest and the number of nuisance events captured by the selected inspection scenario.

Abstract: Various methods, carrier media, and systems for monitoring a characteristic of a specimen are provided. One computer-implemented method for monitoring a characteristic of a specimen includes determining a property of individual pixels on the specimen using output generated by inspecting the specimen with an inspection system. The method also includes determining a characteristic of individual regions on the specimen using the properties of the individual pixels in the individual regions. The method further includes monitoring the characteristic of the specimen based on the characteristics of the individual regions.

Abstract: Systems and methods for design-based inspection using repeating structures are provided.

Abstract: Methods for identifying an edge of a care area for an array area formed on a wafer and/or for binning defects detected in the array area are provided. One method for identifying an edge of a care area for an array area formed on a wafer includes determining a value for a difference image as a function of position from a position known to be inside the array area to a position known to be outside of the array area. The method also includes identifying the position that is located closest to the inside of the array area and that has the value greater than a threshold as a position of the edge of the care area.

Abstract: Various embodiments for determining parameters for wafer inspection and/or metrology are provided.

Abstract: Various methods and systems for determining a defect criticality index (DCI) for defects on wafers are provided. One computer-implemented method includes determining critical area information for a portion of a design for a wafer surrounding a defect detected on the wafer by an inspection system based on a location of the defect reported by the inspection system and a size of the defect reported by the inspection system. The method also includes determining a DCI for the defect based on the critical area information, a location of the defect with respect to the critical area information, and the reported size of the defect.

Abstract: Computer-implemented methods, carrier media, and systems for creating a defect sample for use in selecting one or more parameters of an inspection recipe are provided. One method includes separating defects into bins based on regions in which the defects are located, defect types, and values of the defects for parameter(s) of a detection algorithm. The method also includes determining a number of the defects to be selected from each bin by distributing a user-specified target number of defects across the bins. In addition, the method includes selecting defects from the bins based on the determined numbers thereby creating a defect sample for use in selecting values of parameter(s) of the detection algorithm for use in the inspection recipe.

Abstract: Various embodiments for determining dynamic care areas are provided.

Abstract: Methods and systems for generating information to be used for selecting values for parameter(s) of a detection algorithm are provided. One method includes without user intervention performing a scan of an area of a wafer using an inspection system and default values for parameter(s) of a detection algorithm to detect defects on the wafer. The method also includes selecting a portion of the defects from results of the scan based on a predetermined maximum number of total defects to be used for selecting values for the parameter(s) of the detection algorithm. The method further includes storing information, which includes values for the parameter(s) of the detection algorithm determined for the defects in the portion. The information can be used to select the values for the parameter(s) of the detection algorithm to be used for the inspection recipe without performing an additional scan of the wafer subsequent to the scan.