Abstract: An improved apparatus and method for extracting pattern contour information from an inspection image in a multiple charged-particle beam inspection system are disclosed. An improved method for extracting pattern contour information from an inspection image comprises identifying, from an inspection image obtained from a charged-particle beam inspection system, a first pattern and a second pattern that partially overlap in the inspection image. The method also comprises generating a first separation image by removing an image area corresponding to the second pattern from the inspection image. The first separation image includes the first pattern of which a first part is removed when removing the image area corresponding to the second pattern. The method also comprises updating the first separation image to include image data representing the removed first part of the first pattern based on a first reference image corresponding to the first pattern.

Abstract: Systems and methods for image enhancement are disclosed. A method for enhancing an image may include acquiring a first scanning electron microscopy (SEM) image at a first resolution. The method may also include acquiring a second SEM image at a second resolution. The method may further include providing an enhanced image by using the first SEM image as a reference to enhance the second SEM image. The enhanced image may be provided by using one or more features extracted from the first image to enhance the second SEM image, or using the first SEM image as a reference to numerically enhance the second SEM image.

Abstract: A method for training a machine learning model to generate a predicted measured image, the method including obtaining (a) an input target image associated with a reference design pattern, and (b) a reference measured image associated with a specified design pattern printed on a substrate, wherein the input target image and the reference measured image are non-aligned images; and training, by a hardware computer system and using the input target image, the machine learning model to generate a predicted measured image.

Abstract: A method for training a prediction model to generate a high-resolution image representing defects on a substrate from a low-resolution image of the substrate. The method includes inputting a first image and a reference image of defects on a substrate, which are representative of images captured using different image capture conditions, to a neural network. The neural network is executed to generate a predicted image in response to the first image. A loss function that is indicative of a difference between a defect distribution in the predicted image and a defect distribution in the reference image is calculated and the neural network is modified based on the loss function. The neural network may be trained until the loss function is minimized.

Abstract: Systems and methods for irradiating a sample with a charged-particle beam are disclosed. The charged-particle beam system may comprise a stage configured to hold a sample and is movable in at least one of X-Y-Z axes. The charged-particle beam system may further comprise a position sensing system to determine a lateral and vertical displacement of the stage, and a beam deflection controller configured to apply a first signal to deflect a primary charged-particle beam incident on the sample to at least partly compensate for the lateral displacement, and to apply a second signal to adjust a focus of the deflected charged-particle beam incident on the sample to at least partly compensate for the vertical displacement of the stage. The first and second signals may comprise an electrical signal having a high bandwidth in a range of 10 kHz to 50 kHz, and 50 kHz to 200 kHz, respectively.

Abstract: A method for training a machine learning model to generate a predicted measured image, the method including obtaining (a) an input target image associated with a reference design pattern, and (b) a reference measured image associated with a specified design pattern printed on a substrate, wherein the input target image and the reference measured image are non-aligned images; and training, by a hardware computer system and using the input target image, the machine learning model to generate a predicted measured image.

Abstract: Systems and methods for irradiating a sample with a charged-particle beam are disclosed. The charged-particle beam system may comprise a stage configured to hold a sample and is movable in at least one of X-Y-Z axes. The charged-particle beam system may further comprise a position sensing system to determine a lateral and vertical displacement of the stage, and a beam deflection controller configured to apply a first signal to deflect a primary charged-particle beam incident on the sample to at least partly compensate for the lateral displacement, and to apply a second signal to adjust a focus of the deflected charged-particle beam incident on the sample to at least partly compensate for the vertical displacement of the stage. The first and second signals may comprise an electrical signal having a high bandwidth in a range of 10 kHz to 50 kHz, and 50 kHz to 200 kHz, respectively.

Abstract: A system and method for defect inspection using voltage contrast in a charged particle system are provided. Some embodiments of the system and method include positioning the stage at a first position to enable a first beam of the plurality of beams to scan a first surface area of the wafer at a first time to generate a first image associated with the first surface area; positioning the stage at a second position to enable a second beam of the plurality of beams to scan the first surface area at a second time to generate a second image associated with the first surface area; and comparing the first image with the second image to enable detecting whether a defect is identified in the first surface area of the wafer.

Abstract: An automatic defect classification method may include obtaining a set of image data comprising a set of candidate defects from an inspection tool, developing a plurality of defect review types and a plurality of nuisance review types, and classifying the set of candidate defects according to the defect review types and nuisance review types using a machine learning classifier. Using the plurality of nuisance review types in the classification method reduces a nuisance rate.

Abstract: Systems and methods for image enhancement are disclosed. A method for enhancing an image may include acquiring a first scanning electron microscopy (SEM) image at a first resolution. The method may also include acquiring a second SEM image at a second resolution. The method may further include providing an enhanced image by using the first SEM image as a reference to enhance the second SEM image. The enhanced image may be provided by using one or more features extracted from the first image to enhance the second SEM image, or using the first SEM image as a reference to numerically enhance the second SEM image.

Abstract: Systems and methods for training a machine learning model for defect detection include obtaining training data including an inspection image of a fabricated integrated circuit (IC) and design layout data of the IC, and training a machine learning model using the training data. The machine learning model includes a first autoencoder and a second autoencoder. The first autoencoder includes a first encoder and a first decoder. The second autoencoder includes a second encoder and a second decoder. The second decoder is configured to obtain a first code outputted by the first encoder. The first decoder is configured to obtain a second code outputted by the second encoder.

Abstract: A method for processing images for metrology using a charged particle beam tool may include obtaining, from the charged particle beam tool, an image of a portion of a sample. The method may further include processing the image using a first image processing module to generate a processed image. The method may further include determining image quality characteristics of the processed image and determining whether the image quality characteristics of the processed image satisfy predetermined imaging criteria. The method may further include in response to the image quality characteristics of the processed image not satisfying the imaging criteria, updating a tuning condition of the charged-particle beam tool, acquiring an image of the portion of the sample using the charged-particle beam tool that has the updated tuning condition, and processing the acquired image using the first image processing module to enable the processed acquired image to satisfy the predetermined imaging criteria.

Abstract: Disclosed herein is a method of automatically obtaining training images to train a machine learning model that improves image quality. The method may comprise analyzing a plurality of patterns of data relating to a layout of a product to identify a plurality of training locations on a sample of the product to use in relation to training the machine learning model. The method may comprise obtaining a first image having a first quality for each of the plurality of training locations, and obtaining a second image having a second quality for each of the plurality of training locations, the second quality being higher than the first quality. The method may comprise using the first image and the second image to train the machine learning model.

Abstract: Disclosed herein is a method of automatically obtaining training images to train a machine learning model that improves image quality. The method may comprise analyzing a plurality of patterns of data relating to a layout of a product to identify a plurality of training locations on a sample of the product to use in relation to training the machine learning model. The method may comprise obtaining a first image having a first quality for each of the plurality of training locations, and obtaining a second image having a second quality for each of the plurality of training locations, the second quality being higher than the first quality. The method may comprise using the first image and the second image to train the machine learning model.

Abstract: A system and method for defect inspection using voltage contrast in a charged particle system are provided. Some embodiments of the system and method include positioning the stage at a first position to enable a first beam of the plurality of beams to scan a first surface area of the wafer at a first time to generate a first image associated with the first surface area; positioning the stage at a second position to enable a second beam of the plurality of beams to scan the first surface area at a second time to generate a second image associated with the first surface area; and comparing the first image with the second image to enable detecting whether a defect is identified in the first surface area of the wafer.

Abstract: An improved apparatus and method for enhancing an image, and more particularly an apparatus and method for enhancing an image through cross-talk cancellation in a multiple charged-particle beam inspection are disclosed. An improved method for enhancing an image includes acquiring a first image signal of a plurality of image signals from a detector of a multi-beam inspection system. The first image signal corresponds to a detected signal from a first region of the detector on which electrons of a first secondary electron beam and of a second secondary electron beam are incident. The method includes reducing, from the first image signal, cross-talk contamination originating from the second secondary electron beam using a relationship between the first image signal and beam intensities associated with the first secondary electron beam and the second secondary electron beam. The method further includes generating a first image corresponding to first secondary electron beam after reduction.

Abstract: Systems and methods for image analysis include obtaining a plurality of simulation images and a plurality of non-simulation images both associated with a sample under inspection, at least one of the plurality of simulation images being a simulation image of a location on the sample not imaged by any of the plurality of non-simulation images; and training an unsupervised domain adaptation technique using the plurality of simulation images and the plurality of non-simulation images as inputs to reduce a difference between first intensity gradients of the plurality of simulation images and second intensity gradients of the plurality of non-simulation images.

Abstract: Apparatuses, systems, and methods for providing beams for defect detection and defect location identification associated with a sample of charged particle beam systems. In some embodiments, a method may include obtaining an image of a sample; determining defect characteristics from the image; generating an updated image based on the determined defect characteristics and the image; and aligning the updated image with a reference image.

Abstract: An improved systems and methods for correcting distortion of an inspection image are disclosed. An improved method for correcting distortion of an inspection image comprises acquiring an inspection image, aligning a plurality of patches of the inspection image based on a reference image corresponding to the inspection image, evaluating, by a machine learning model, alignments between each patch of the plurality of patches and a corresponding patch of the reference image, determining local alignment results for the plurality of patches of the inspection image based on a reference image corresponding to the inspection image, determining an alignment model based on the local alignment results, and correcting a distortion of the inspection image based on the alignment model.

Abstract: Systems and methods for detecting a defect on a sample include receiving a first image and a second image associated with the first image; determining, using a clustering technique, N first feature descriptor(s) for L first pixel(s) in the first image and M second feature descriptor(s) for L second pixel(s) in the second image, wherein each of the L first pixel(s) is co-located with one of the L second pixel(s), and L, M, and N are positive integers; determining K mapping probability between a first feature descriptor of the N first feature descriptor(s) and each of K second feature descriptor(s) of the M second feature descriptor(s), wherein K is a positive integer; and providing an output for determining whether there is existence of an abnormal pixel representing a candidate defect on the sample based on a determination that one of the K mapping probability does not exceed a threshold value.