Abstract: Implementations of the disclosure provide methods for generating an in-die reference for die-to-die defect detection techniques. The inspection methods using in-die reference comprise finding similar blocks of a lithographic mask, the similar blocks are defined by similar CAD information. A comparison distance is selected based on (i) areas of the similar blocks and (ii) spatial relationships between the similar blocks. The similar blocks are aggregated, based on the comparison distance, to provide multiple aggregated areas; and comparable regions of the lithographic mask are defined based on the multiple aggregate blocks. Images of at least some of the comparable regions of the lithographic mask are acquired using an inspection module. The acquired images are compared.

Abstract: There are provided system and method of examining a semiconductor specimen. The method comprises: upon obtaining a Deep Neural Network (DNN) trained for a given examination-related application within a semiconductor fabrication process, processing together one or more fabrication process (FP) images using the obtained trained DNN, wherein the DNN is trained using a training set comprising ground truth data specific for the given application; and obtaining examination-related data specific for the given application and characterizing at least one of the processed one or more FP images. The examination-related application can be, for example, classifying at least one defect presented by at least one FP image, segmenting the at least one FP image, detecting defects in the specimen presented by the at least one FP image, registering between at least two FP images, regression application enabling reconstructing the at least one FP image in correspondence with different examination modality, etc.

Abstract: There is provided a system and method of generating a training set usable for examination of a semiconductor specimen. The method comprises: obtaining a simulation model capable of simulating effect of a physical process on fabrication process (FP) images depending on the values of parameters of the physical process; applying the simulation model to an image to be augmented for the training set and thereby generating one or more augmented images corresponding to one or more different values of the parameters of the physical process; and including the generated one or more augmented images into the training set. The training set can be usable for examination of the specimen using a trained Deep Neural Network, automated defect review, automated defect classification, automated navigation during the examination, automated segmentation of FP images, automated metrology based on FP images and other examination processes that include machine learning.

Abstract: A system of classifying a pattern of interest (POI) on a semiconductor specimen, the system comprising a processor and memory circuitry configured to: obtain a high-resolution image of the POI, and generate data usable for classifying the POI in accordance with a defectiveness-related classification, wherein the generating utilizes a machine learning model that has been trained in accordance with training samples comprising: a high-resolution training image captured by scanning a respective training pattern on a specimen, the respective training pattern being similar to the POI, and a label associated with the image, the label being derivative of low-resolution inspection of the respective training pattern.

Abstract: There is provided a system comprising a processor configured to obtain a set of images of a semiconductor specimen, (1) for an image of the set of images, select at least one algorithmic module MS out of a plurality of algorithmic modules, (2) feed the image to MS to obtain data DMS representative of one or more defects in the image, (3) obtain a supervised feedback regarding rightness of data DMS, (4) repeat (1) to (3) for a next image until a completion criterion is met, wherein an algorithmic module selected at (1) is different for at least two different images of the set of images, generate, based on the supervised feedback, a score for each of a plurality of the algorithmic modules, and use scores to identify one or more algorithmic modules Mbest as the most adapted for providing data representative of one or more defects in the set of images.

Abstract: There is provided a system comprising a processor configured to obtain a set of images of a semiconductor specimen, (1) for an image of the set of images, select at least one algorithmic module MS out of a plurality of algorithmic modules, (2) feed the image to MS to obtain data DMS representative of one or more defects in the image, (3) obtain a supervised feedback regarding rightness of data DMS, (4) repeat (1) to (3) for a next image until a completion criterion is met, wherein an algorithmic module selected at (1) is different for at least two different images of the set of images, generate, based on the supervised feedback, a score for each of a plurality of the algorithmic modules, and use scores to identify one or more algorithmic modules Mbest as the most adapted for providing data representative of one or more defects in the set of images.

Abstract: A system, method and computer readable medium for classifying defects, the method comprising: receiving classified first defects, and potential defects, each first and potential defect having values for attributes; processing the first and potential defects to select a subset of the attributes that differentiates the first defects from the potential defects; obtaining first and second functions based on the first defects and potential defects, respectively; obtaining a first threshold for the first function, and a second threshold for a combination of the first and second functions; applying the first function and the second function to each potential defect to obtain first and second scores, respectively; and determining a combined score of the first and second scores; and indicating as a defect of a potentially new type a potential defect when the first score is lower than the first threshold or the combined score exceeds the second threshold.

Abstract: A system, method and computer software product, the system capable of classifying defects and comprising: an hardware-based GUI component; and a processing and memory circuitry configured to: a. upon obtaining data informative of a plurality of defects and attribute values thereof, using the attribute values to create initial classification of the plurality of defects into a plurality of classes; b. for a given class, presenting to a user, by the hardware-based GUI component, an image of a defect initially classified to the given class with a low likelihood, wherein the image is presented along with images of one or more defects initially classified to the given class with the highest likelihood; and c. subject to confirming by the user, using the hardware-based GUI component, that the at least one defect is to be classified to the given class, indicating the at least one defect as belonging to the given class.

Abstract: There is provided a method and a system configured to obtain an image of a one or more first areas of a semiconductor specimen acquired by an examination tool, determine data Datt informative of defectivity in the one or more first areas, determine one or more second areas of the semiconductor specimen for which presence of a defect is suspected based at least on an evolution of Datt, or of data correlated to Datt, in the one or more first areas, and select the one or more second areas for inspection by the examination tool.

Abstract: A system, method and computer readable medium for examining a specimen, the method comprising: obtaining defects of interest (DOIs) and false alarms (FAs) from a review subset selected from a group of potential defects received from an inspection tool, each potential defect is associated with attribute values defining a location of the potential defect in an attribute space; generating a representative subset of the group, comprising potential defects selected in accordance with a distribution of the potential defects within the attribute space, and indicating the potential defects in the representative subset as FA; and upon training a classifier using data informative of the attribute values of the DOIs, the potential defects of the representative subset, and respective indications thereof as DOIs or FAs, applying the classifier to at least some of the potential defects to obtain an estimation of a number of expected DOIs in the specimen.

Abstract: Implementations of the disclosure provide methods for generating an in-die reference for die-to-die defect detection techniques. The inspection methods using in-die reference comprise finding similar blocks of a lithographic mask, the similar blocks are defined by similar CAD information. A comparison distance is selected based on (i) areas of the similar blocks and (ii) spatial relationships between the similar blocks. The similar blocks are aggregated, based on the comparison distance, to provide multiple aggregated areas; and comparable regions of the lithographic mask are defined based on the multiple aggregate blocks. Images of at least some of the comparable regions of the lithographic mask are acquired using an inspection module. The acquired images are compared.

Abstract: There is provided a method of defect detection on a specimen and a system thereof. The method includes: obtaining a runtime image representative of at least a portion of the specimen; processing the runtime image using a supervised model to obtain a first output indicative of the estimated presence of first defects on the runtime image; processing the runtime image using an unsupervised model component to obtain a second output indicative of the estimated presence of second defects on the runtime image; and combining the first output and the second output using one or more optimized parameters to obtain a defect detection result of the specimen.

Abstract: There are provided a classifier and a method of classifying defects in a semiconductor specimen. The classifier enables assigning each class to a classification group among three or more classification groups with different priorities. Classifier further enables setting purity, accuracy and/or extraction requirements separately for each class, and optimizing the classification results in accordance with per-class requirements. During training, the classifier is configured to generate a classification rule enabling the highest possible contribution of automated classification while meeting per-class quality requirements defined for each class.

Abstract: There are provided system and method of segmentation a fabrication process (FP) image obtained in a fabrication of a semiconductor specimen. The method comprises: upon obtaining a Deep Neural Network (DNN) trained to provide segmentation-related data, processing a fabrication process (FP) sample using the obtained trained DNN and, resulting from the processing, obtaining by the computer segments-related data characterizing the FP image to be segmented, the obtained segments-related data usable for automated examination of the semiconductor specimen. The DNN is trained using a segmentation training set comprising a plurality of first training samples and ground truth data associated therewith, each first training sample comprises a training image; FP sample comprises the FP image to be segmented.

Abstract: There is provided a mask inspection system and a method of mask inspection. The method comprises: during a runtime scan of a mask of a semiconductor specimen, processing a plurality of aerial images of the mask acquired by the mask inspection system to calculate a statistic-based Edge Positioning Displacement (EPD) of a potential defect, wherein the statistic-based EPD is calculated using a Print Threshold (PT) characterizing the mask and is applied to each of the one or more acquired aerial images to calculate respective EPD of the potential defect therein; and filtering the potential defect as a “runtime true” defect when the calculated statistic-based EPD exceeds a predefined EPD threshold, and filtering out the potential defect as a “false” defect when the calculated statistic-based EPD is lower than the predefined EPD threshold. The method can further comprise after-runtime EPD-based filtering of the plurality of “runtime true” defects.

Abstract: An examination system, a method of obtaining a training set for a classifier, and a non-transitory computer readable medium, the method comprising: upon receiving in a memory device object inspection results comprising data indicative of potential defects, each potential defect of the potential defects associated with a multiplicity of attribute values defining a location of the potential defect in an attribute space: sampling by the processor a first set of defects from the potential defects, wherein the defects within the first set are dispersed independently of a density of the potential defects in the attribute space; and obtaining by the processor a training defect sample set comprising the first set of defects and data or parameters representative of the density of the potential defects in the attribute space.

Abstract: There is provided a method of examination of a semiconductor specimen. The method comprises: upon obtaining by a computer a Deep Neural Network (DNN) trained for a given examination-related application within a semiconductor fabrication process, processing together one or more fabrication process (FP) images using the obtained trained DNN, wherein the DNN is trained using a training set comprising synthetic images specific for the given application; and obtaining, by the computer, examination-related data specific for the given application, and characterizing at least one of the processed one or more FP images. Generating the training set can comprise: training an auxiliary DNN to generate a latent space, generating a synthetic image by applying the trained auxiliary DNN to a point selected in the generated latent space, and adding the generated synthetic image to the training set.

Abstract: A captured image of a pattern and a reference image of the pattern may be received. A contour of interest of the pattern may be identified. One or more measurements of a dimension of the pattern may be determined for each of the reference image and the captured image with respect to the contour of interest of the pattern. A defect associated with the contour of interest may be classified based on the determined one or more measurements of the dimension of the pattern for each of the reference image and the captured image.

Abstract: There is provided a method of examination of a semiconductor specimen and a system thereof. The method comprises: using a trained Deep Neural Network (DNN) to process a fabrication process (FP) sample, wherein the FP sample comprises first FP image(s) received from first examination modality(s) and second FP image(s) received from second examination modality(s) which differs from the first examination modality(s), and wherein the trained DNN processes the first FP image(s) separately from the second FP image(s); and further processing by the trained DNN the results of such separate processing to obtain examination-related data specific for the given application and characterizing at least one of the processed FP images. When the FP sample further comprises numeric data associated with the FP image(s), the method further comprises processing by the trained DNN at least part of the numeric data separately from processing the first and the second FP images.

Abstract: A system, method and computer readable medium for classifying defects, the method comprising: receiving classified first defects, and potential defects, each first and potential defect having values for attributes; processing the first and potential defects to select a subset of the attributes that differentiates the first defects from the potential defects; obtaining first and second functions based on the first defects and potential defects, respectively; obtaining a first threshold for the first function, and a second threshold for a combination of the first and second functions; applying the first function and the second function to each potential defect to obtain first and second scores, respectively; and determining a combined score of the first and second scores; and indicating as a defect of a potentially new type a potential defect when the first score is lower than the first threshold or the combined score exceeds the second threshold.