Abstract: In anomaly determination using an autoencoder, the present invention enables highly accurate anomaly determination with respect to an unknown anomaly image, even in the case of learning using only a non-defective image. In a learning step of learning a parameter of the autoencoder using a non-defective learning image /{f_i/} captured of a non-defective test target, an anomaly determination accuracy rate Rc of the non-defective learning image /{f_i/} is used as an evaluation value, and a dimension compression rate Rd of a code layer of the autoencoder is maximized or an input signal amount to the code layer or an output signal amount from the code layer is decreased, such that the anomaly determination accuracy rate Rc is maximized or becomes at least a predetermined threshold th.

Abstract: A defect observation method includes, as steps executed by a computer system, a first step of acquiring, as a bevel image, an image captured using defect candidate coordinates in a bevel portion as an imaging position by using a microscope or an imaging apparatus; and a second step of detecting a defect in the bevel image. The second step includes a step of determining whether there is at least one portion among a wafer edge, a wafer notch, and an orientation flat in the bevel image, a step of switching and selectively applying a defect detection scheme of detecting the defect from the bevel image from a plurality of schemes which are candidates based on a determination result, and a step of executing a process of detecting the defect from the bevel image in conformity with the switched scheme.

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: In a learning phase, a processor of a sample observation device: stores design data on a sample in a storage resource; creates a first learning image as a plurality of input images; creates a second learning image as a target image; and learns a model related to image quality conversion with the first and second learning images. In a sample observation phase, the processor obtains, as an observation image, a second captured image output by inputting a first captured image obtained by imaging the sample with an imaging device to the model. The processor creates at least one of the first and second learning images based on the design data.

Abstract: The present invention includes image acquiring for acquiring an inspection image of a target object, pass/fail determining for determining whether the inspection image acquired in the image acquiring is the inspection image of a non-defect candidate or the inspection image of a defect candidate, overdetection determining for determining whether the inspection image determined as a defect candidate in the pass/fail determining is the inspection image of overdetection or the inspection image of non-overdetection which is not overdetection, non-defect estimation parameter learning for learning a non-defect estimation parameter used in the pass/fail determining using a learning non-defect image acquired in the image acquiring, and overdetection determination parameter learning for learning an overdetection determination parameter used in the overdetection determining using the learning non-defect 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: A sample observation device images a sample placed on a movable table by irradiating and scanning the sample with a charged particle beam of a microscope. A degraded image having poor image quality and a high quality image having satisfactory image quality which are acquired at the same location of the sample by causing the charged particle microscope to change an imaging condition for imaging the sample are stored. An estimation process parameter is calculated for estimating the high quality image from the degraded image by using the stored degraded image and high quality image. A high quality image estimation unit processes the degraded image obtained by causing the charged particle microscope to image the desired site of the sample by using the calculated estimation process parameter. Thereby, the high quality image obtained at the desired site is estimated, and then the estimated high quality image is output.

Abstract: A defect observation device comprising: a defect determination coordinate creation unit by which the coordinates of a plurality of second defect candidates are determined as overlapping defect candidate coordinates, the plurality of second defect candidates respectively having, in a plurality of second imaging visual field regions overlapping a first imaging visual field region, a circuit pattern which partly overlaps a circuit pattern in the first imaging visual field region, in which a first defect candidate for defect determination among a plurality of defect candidates of a sample is present; a pseudo-reference image generation unit which generates a pseudo-reference image including a circuit pattern of the first defect candidate by superimposing a plurality of images respectively captured at the plurality of overlapping defect candidate coordinates; and a defect determination unit which compares an image for defect determination captured at the coordinates of the first defect candidate with the pseudo-re

Abstract: A versatile template generation unit cuts a first region in which a similarity level to a template image is a first similarity level and a second region in which the similarity level to the template image is a second similarity level different from the first similarity level, from an input image including an alignment mark, to generate a versatile template image.

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: Provided is a defect classification apparatus classifying images of defects of a sample included in images obtained by capturing the sample, the apparatus including an image storage unit for storing the images of the sample acquired by an external image acquisition unit, a defect class storage unit for storing types of defects included in the images of the sample, an image processing unit for extracting images of defects from the images from the sample, processing the extracted images of defects and generating a plurality of defect images, a classifier learning unit for learning a defect classifier using the images of defects of the sample extracted by the image processing unit and data of the plurality of generated defect images, and a defect classification unit for processing the images of the sample by using the classifier learned by the classifier learning unit, to classify the images of defects of the sample.

Abstract: A sample observation device images a sample placed on a movable table by irradiating and scanning the sample with a charged particle beam of a microscope. A degraded image having poor image quality and a high quality image having satisfactory image quality which are acquired at the same location of the sample by causing the charged particle microscope to change an imaging condition for imaging the sample are stored. An estimation process parameter is calculated for estimating the high quality image from the degraded image by using the stored degraded image and high quality image. A high quality image estimation unit processes the degraded image obtained by causing the charged particle microscope to image the desired site of the sample by using the calculated estimation process parameter. Thereby, the high quality image obtained at the desired site is estimated, and then the estimated high quality image is output.

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: A sample observation device images a sample placed on a movable table by irradiating and scanning the sample with a charged particle beam of a microscope. A degraded image having poor image quality and a high quality image having satisfactory image quality which are acquired at the same location of the sample by causing the charged particle microscope to change an imaging condition for imaging the sample are stored. An estimation process parameter is calculated for estimating the high quality image from the degraded image by using the stored degraded image and high quality image. A high quality image estimation unit processes the degraded image obtained by causing the charged particle microscope to image the desired site of the sample by using the calculated estimation process parameter. Thereby, the high quality image obtained at the desired site is estimated, and then the estimated high quality image is output.

Abstract: A defect observation device comprising: a defect determination coordinate creation unit by which the coordinates of a plurality of second defect candidates are determined as overlapping defect candidate coordinates, the plurality of second defect candidates respectively having, in a plurality of second imaging visual field regions overlapping a first imaging visual field region, a circuit pattern which partly overlaps a circuit pattern in the first imaging visual field region, in which a first defect candidate for defect determination among a plurality of defect candidates of a sample is present; a pseudo-reference image generation unit which generates a pseudo-reference image including a circuit pattern of the first defect candidate by superimposing a plurality of images respectively captured at the plurality of overlapping defect candidate coordinates; and a defect determination unit which compares an image for defect determination captured at the coordinates of the first defect candidate with the pseudo-re

Abstract: A versatile template generation unit cuts a first region in which a similarity level to a template image is a first similarity level and a second region in which the similarity level to the template image is a second similarity level different from the first similarity level, from an input image including an alignment mark, to generate a versatile template image.

Abstract: Provided is a defect classification apparatus classifying images of defects of a sample included in images obtained by capturing the sample, the apparatus including an image storage unit for storing the images of the sample acquired by an external image acquisition unit, a defect class storage unit for storing types of defects included in the images of the sample, an image processing unit for extracting images of defects from the images from the sample, processing the extracted images of defects and generating a plurality of defect images, a classifier learning unit for learning a defect classifier using the images of defects of the sample extracted by the image processing unit and data of the plurality of generated defect images, and a defect classification unit for processing the images of the sample by using the classifier learned by the classifier learning unit, to classify the images of defects of the sample.