Abstract: The present disclosure proposes a system for detecting a foreign material adhering to or a scratch formed on a bevel at an edge of a semiconductor wafer in order to detect the foreign material or defect on the bevel without using a reference image and including a learning device (905) that outputs information on the foreign material adhering to or the scratch formed on the bevel as a learning result, in which the learning device performs learning in advance by using image data acquired by an image acquisition tool and the information on the foreign material or the scratch on the bevel included in the image data, and the foreign material or the scratch is detected by inputting the image data obtained by the image acquisition tool to the learning device (refer to FIG. 9).

Abstract: An object of the present disclosure is to provide a defect classification device capable of easily grasping an appropriate recipe update timing of an imaging device when classification accuracy for classifying defects existing on a semiconductor wafer is decreased. The defect classification device according to the present disclosure calculates classification accuracy by further acquiring a result of a manual classification for defects spanning a plurality of classification spaces as a result of an automatic classification, and comparing the result of the automatic classification with the result of the manual classification (see FIG. 5).

Abstract: A machine learning system and a machine learning method capable of selecting a pretrained model to be used in transfer learning in a short time without actually executing the transfer learning includes a pretrained model acquisition unit which acquires a pretrained model from a pretrained model storage unit storing a plurality of pretrained models obtained by learning a transfer source task under respective conditions; a transfer learning dataset storage unit configured to store dataset related to a transfer target task; a pretrained model adaptability evaluation unit configured to evaluate adaptability of each pretrained model acquired by the pretrained model acquisition unit to the dataset related to the transfer target task; and a transfer learning unit configured to execute, based on an evaluation result of the pretrained model adaptability evaluation unit, transfer learning using a selected pretrained model and the dataset, and outputs a learning result as a trained model.

Abstract: Provided is a wafer observation apparatus includes: a scanning electron microscope; a control unit which includes a wafer observation unit that observes a wafer of a semiconductor device, and an image acquisition unit that acquires a wafer image; a storage unit which includes an image storage unit that stores the wafer image and a template image, and a recipe storage unit that stores a wafer alignment recipe including a matching success and failure determination threshold value, an image processing parameter set, and a use priority associated with the template image; and a calculation unit which includes a recipe reading unit that reads the template image and the wafer alignment recipe, a recipe update necessity determination unit that determines update necessity of the wafer alignment recipe, and a recipe updating unit that updates the wafer alignment recipe based on a determination result in the recipe update necessity determination unit.

Abstract: A defect inspecting system includes a detector configured to image a sample and a host control device that acquires an inspection image including a defect and a plurality of reference images not including a defect site and generates a pseudo defect image by editing a predetermined reference image among the plurality of acquired reference images. An initial parameter is determined with which the pseudo defect site is detectable from the pseudo defect image. The host control device acquires a defect candidate site from the inspection image using the initial parameter, estimates a high-quality image from an image of a site corresponding to the defect candidate site using the parameter acquired in image quality enhancement, and specifies an actual defect site in the inspection image by executing defect discrimination. A parameter is determined with which a site close to the specified actual defect site is detectable using the inspection image.

Abstract: The invention provides a sample observation system including a scanning electron microscope and a calculator. The calculator: (1) acquires a plurality of images captured by the scanning electron microscope; (2) acquires, from the plurality of images, a learning defect image including a defect portion and a learning reference image not including the defect portion; (3) calculates estimation processing parameters by using the learning defect image and the learning reference image; (4) acquires an inspection defect image including a defect portion; and (5) estimates a pseudo reference image by using the estimation processing parameters and the inspection defect image.

Abstract: In learning processing performed before sample observation processing (steps S705 to S708), the sample observation device acquires a low-picture quality learning image under a first imaging condition for each defect position indicated by defect position information, determines an imaging count of a plurality of high-picture quality learning images associated with the low-picture quality learning image for each defect position and a plurality of imaging points based on a set value of the imaging count, acquires the plurality of high-picture quality learning images under a second imaging condition (step S702), learns a high-picture quality image estimation model using the low-picture quality learning image and the plurality of high-picture quality learning images (step S703), and adjusts a parameter related to the defect detection in the sample observation processing using the high-picture quality image estimation model (step S704).

Abstract: Provided is a technique capable of achieving both throughput and robustness for a function of adjusting brightness (B) and contrast (C) of a captured image in a charged particle beam device. The charged particle beam device includes a computer system having a function (ABCC function) of adjusting the B and the C of an image obtained by imaging a sample. The computer system determines whether adjustment is necessary based on a result obtained by evaluating a first image obtained by imaging an imaging target of the sample (step S2), executes, when the adjustment is necessary based on a result of the determination, the adjustment on a second image of the imaging target to set an adjusted B value and an adjusted C value (step S4), and captures a third image of the imaging target based on the adjusted setting values to generate an image for observation (step S5).

Abstract: Provided is a technique capable of achieving both throughput and robustness for a function of adjusting brightness (B) and contrast (C) of a captured image in a charged particle beam device. The charged particle beam device includes a computer system having a function (ABCC function) of adjusting the B and the C of an image obtained by imaging a sample. The computer system determines whether adjustment is necessary based on a result obtained by evaluating a first image obtained by imaging an imaging target of the sample (step S2), executes, when the adjustment is necessary based on a result of the determination, the adjustment on a second image of the imaging target to set an adjusted B value and an adjusted C value (step S4), and captures a third image of the imaging target based on the adjusted setting values to generate an image for observation (step S5).

Abstract: A defect observation device is configured to include a charged particle microscope and a controller including a control unit that controls the charged particle microscope, a storage unit, and an arithmetic unit, in which the control unit controls the charged particle microscope under a first condition to acquire a first image of an observation target region of the sample, the arithmetic unit extracts first position information of the observation target region from the obtained first image, the control unit controls the charged particle microscope under a second condition to acquire a second image of the observation target region of the sample, and the arithmetic unit performs an image quality conversion process to match the image quality of the acquired second image with the image quality of the first image using the image quality conversion process parameters to process the second image subjected to the image quality conversion process.

Abstract: In a device for observing a semiconductor wafer, a positional relationship between an in-wafer region and a background region in an imaging field of view is not constant when an outer peripheral portion of the wafer is imaged, which results in an increase in the quantity of calculation in defect detection and image classification processing and makes it difficult to efficiently perform defect observation and analysis. There is provided a defect observation system for a semiconductor wafer, and the system includes: a stage on which the semiconductor wafer is placed and which is movable in an XY direction, an imaging unit that is configured to image a portion including an edge of the semiconductor wafer, and an image output unit that is configured to, with respect to a plurality of images obtained by imaging, output images in which edges of the wafer are substantially in parallel among the plurality of images.

Abstract: Provided is a wafer observation apparatus includes: a scanning electron microscope; a control unit which includes a wafer observation unit that observes a wafer of a semiconductor device, and an image acquisition unit that acquires a wafer image; a storage unit which includes an image storage unit that stores the wafer image and a template image, and a recipe storage unit that stores a wafer alignment recipe including a matching success and failure determination threshold value, an image processing parameter set, and a use priority associated with the template image; and a calculation unit which includes a recipe reading unit that reads the template image and the wafer alignment recipe, a recipe update necessity determination unit that determines update necessity of the wafer alignment recipe, and a recipe updating unit that updates the wafer alignment recipe based on a determination result in the recipe update necessity determination unit.

Abstract: A defect observation device is configured to include a charged particle microscope and a controller including a control unit that controls the charged particle microscope, a storage unit, and an arithmetic unit, in which the control unit controls the charged particle microscope under a first condition to acquire a first image of an observation target region of the sample, the arithmetic unit extracts first position information of the observation target region from the obtained first image, the control unit controls the charged particle microscope under a second condition to acquire a second image of the observation target region of the sample, and the arithmetic unit performs an image quality conversion process to match the image quality of the acquired second image with the image quality of the first image using the image quality conversion process parameters to process the second image subjected to the image quality conversion process.

Abstract: A defect observation device detects a defect with high accuracy regardless of a defect size. One imaging configuration for observing an observation target on a sample is selected from an optical microscope, an optical microscope, and an electron microscope, and an imaging condition of the selected imaging configuration is controlled.

Abstract: A defect observation apparatus includes a storage unit configured to store defect information about defects detected by an external inspection apparatus; a first imaging unit configured to capture an image of a defect using a first imaging condition and a second imaging condition; a control unit configured to correct positional information on the defect using the image captured with the first imaging unit; and a second imaging unit configured to capture an image of the defect based on the corrected positional information.

Abstract: In a device for observing a semiconductor wafer, a positional relationship between an in-wafer region and a background region in an imaging field of view is not constant when an outer peripheral portion of the wafer is imaged, which results in an increase in the quantity of calculation in defect detection and image classification processing and makes it difficult to efficiently perform defect observation and analysis. There is provided a defect observation system for a semiconductor wafer, and the system includes: a stage on which the semiconductor wafer is placed and which is movable in an XY direction, an imaging unit that is configured to image a portion including an edge of the semiconductor wafer, and an image output unit that is configured to, with respect to a plurality of images obtained by imaging, output images in which edges of the wafer are substantially in parallel among the plurality of images.

Abstract: To review minute defects that were buried in roughness scattered light with an observation device provided with a dark-field microscope, a scanning electron microscope (SEM), and a control unit, the present invention configures the dark-field microscope by installing a filter for blocking a portion of the scattered light, an imaging lens for focusing the scattered light that has passed through the filter, and a detector for dividing the image of the scattered light focused by the imaging lens into the polarization directions converted by a wavelength plate and detecting the resulting images, and the control has a calculation unit for determining the position of a defect candidate detected by another inspection device using the plurality of images separated into polarization directions and detected by the detector.

Abstract: A defect observation device detects a defect with high accuracy regardless of a defect size. One imaging configuration for observing an observation target on a sample is selected from an optical microscope, an optical microscope, and an electron microscope, and an imaging condition of the selected imaging configuration is controlled.

Abstract: To quantify the degree of a defect, and provide information useful for yield management. Disclosed is a defect quantification method wherein: a defect image is classified; a measurement region and a measurement area are set to each of the defect image and a reference image on the basis of defect image classification results, said reference image corresponding to the defect image; and an evaluation value of a defect is calculated using each of the measurement values obtained from each of the measurement areas of the defect image and the reference image, and the defect is quantified.

Abstract: Provided is a GUI including: an unadded pane region that hierarchically displays folders which are sets of images having no class information added thereto; an image pane region that displays the images displayed in the unadded pane region, the displayed images having no classification added thereto; and a class pane region that displays images having classification added thereto, wherein by externally inputting class information for one image having the class information added thereto, the input class information is displayed.