Abstract: Provided is an image inspection device which can prevent a degradation in the accuracy of an estimation value of a probability distribution caused by position displacement between design data and a captured image in image processing in which a model that estimates a pixel value probability distribution of a captured image is trained by using design data and the captured image of a sample.

Abstract: Provided are a defect inspection apparatus and a defect inspection method that can inspect various types of defects in a synthesized image. The defect inspection apparatus synthesizes a first detection signal from a first detector and a second detection signal from a second detector with a first synthesis ratio to generate a first synthesized image, and synthesizes the first detection signal and the second detection signal with a second synthesis ratio different from the first synthesis ratio to generate a second synthesized image. The defect inspection apparatus generates a first inspection image based on the first synthesized image and generates a second inspection image based on the second synthesized image. The defect inspection apparatus executes a logical operation on the first inspection image and the second inspection image to generate a synthesized inspection image. The defect inspection apparatus executes defect determination on the synthesized inspection image.

Abstract: The purpose of the present invention is to provide a computer program for achieving die-to-database inspection at high speed and with few false reports, and a semiconductor inspection device using the same. To achieve this purpose, the present invention proposes: a computer program comprising an encoder layer that is configured to determine the features of a design data image, and a decoder layer that is configured to generate, on the basis of a variation in an image (inspection target image) obtained by photographing an inspection target pattern, a statistic pertaining to the brightness values of pixels from feature values output by the encoder layer, wherein die-to-database inspection with few false reports can be achieved by comparing the inspection target image and the statistic obtained from the decoder layer and pertaining to the brightness values, and thereby detecting a defect region in the image; and a semiconductor inspection device using the same.

Abstract: An inspection apparatus includes an image distortion estimation unit that estimates a distortion amount between a reference image and an inspection image, an image distortion correction unit that corrects the inspection image and/or the reference image using an estimated distortion amount, and an inspection unit that performs inspection using a corrected inspection image and the reference image or the inspection image and a corrected reference image. The image distortion estimation unit estimates a distortion amount in which only distortion occurring in an entire image can be corrected by adjustment of a correction condition.

Abstract: A robot inspection system includes a coupling unit to which a mount table with a robot mounted thereon is coupled, a positioning mechanism positioning the coupling unit and the mount table, and an inspection unit performing an inspection of the robot with the mount table coupled to the coupling unit. Further, the mount table is transported to the coupling unit by an automatic guided vehicle. Furthermore, the inspection unit performs a plurality of types of inspections on the robot. Moreover, the coupling unit includes a recessed portion having an entry opening entered by the mount table, and the inspection unit is placed around the recessed portion.

Abstract: In order to select an optimal learning model for an image when inference is carried out in the extraction of a profile line using machine learning, without requiring a correct value or degree of certainty, a feature extraction learning model group containing a plurality of learning models is used for feature extraction. A recall learning model group containing recall learning models is paired with the feature extraction learning models. A feature amount extraction unit for referencing a feature extraction learning model and extracting a feature amount from input data; a data-to-data recall unit for referencing a recall learning model and outputting a recall result with the feature amount subjected to dimensional compression; and a learning model selection unit for selecting a feature extraction learning model from the feature extraction learning model group under the condition that the difference between the feature amount and the recall result is minimized are provided.

Abstract: A defect inspection apparatus includes: a feature value calculation unit calculating a feature value based on a captured image of a sample; an image information reduction unit generating a latent variable by reducing an information quantity of the feature value; a statistic value estimation unit estimating an image statistic value that can be taken by a normal image based on the latent variable; and a defect detection unit detecting a defect in an inspection image based on the image statistic value and the inspection image of the sample.

Abstract: An object of the present invention is to achieve both suppression of data amount of an image processing system that learns a collation image to be used for image identification using a discriminator and improvement of identification performance of the discriminator. In order to achieve the above object, there is proposed an image processing system including a discriminator that identifies an image using a collation image, the image processing system further including a machine learning engine that performs machine learning of collation image data required for image identification. The machine learning engine searches for a successfully identified image using an image for which identification has been failed, and adds information, obtained based on a partial image of the image for which identification has been failed and which has been selected by an input device to the successfully identified image obtained by the search to generate corrected collation image data.

Abstract: An image processing method whereby data pertaining to an estimated captured image obtained from reference data of a sample is acquired using an input acceptance unit, an estimation unit, and an output unit. The data is used when comparing the estimated image and an actual image of the sample, wherein the method includes: an input acceptance unit accepting input of the reference data, process information pertaining to the sample, and trained model data; the estimation unit using the reference data, the process information, and the model data to calculate captured image statistics representing a probabilistic distribution of values attained by the data of the captured image; and the output unit outputting the captured image statistics, and generating the estimated captured image from the captured image statistics. This permits reducing the time required for estimation and to perform comparison in real time.

Abstract: An object of the disclosure is to provide a pattern inspection and measurement apparatus that can accurately specify a corner point formed on a sample. The pattern inspection and measurement apparatus according to the disclosure specifies a pair of corner points as a corner pair candidate on design data, and specifies a corner point on an actually formed shape pattern in accordance with a relative relation between the corner pair candidate on the design data and the corner pair candidate in the shape pattern (see FIG. 13).

Abstract: A defect inspection system includes: a defect detection unit that detects defect positions in an inspection image by comparing an inspection image with a reference image that is an image having no defect; a filter model that classifies detected defect positions into false defect or a designated type of defect; a filter condition holding unit that holds a filter condition; a defect region extraction unit that collects the defect positions detected by the defect detection unit for each predetermined distance; a defect filter unit that determines whether or not each defect region satisfies the filter condition and extracts only the defect region that satisfies the filter condition; and a normalization unit that normalizes the inspection image based on a processing step at the time of inspection and a normalization condition set for each processing step or each imaging condition.

Abstract: A pattern inspection system inspects an image of an inspection target pattern of an electronic device using an identifier constituted by machine learning, based on the image of the inspection target pattern of the electronic device and data used to manufacture the inspection target pattern. The system includes a storage unit which stores a plurality of pattern images of the electronic device and pattern data used to manufacture a pattern of the electronic device, and an image selection unit which selects a learning pattern image used in the machine learning from the plurality of pattern images, based on the pattern data and the pattern image stored in the storage unit.

Abstract: A learning processing device and method achieves learning of a lightweight model that is completed in a short amount of time. The learning processing device obtains a new, second learning model from an existing first learning model. An input unit acquires a first learning model generated in advance by learning a first learning data set, and an unpruned neural network (hereinafter, NN). An important parameter identification unit uses the first learning model and the NN to initialize a NN to be learned, and uses a second learning data set and the initialized NN to identify a degree of importance of parameters in a recognition process of the initialized NN. A new model generation unit carries out a pruning process for deleting parameters which are not important from the initialized NN, thereby generating a second NN; and a learning unit uses the second learning data set to learn the second NN.

Abstract: An inspection apparatus includes an image distortion estimation unit that estimates a distortion amount between a reference image and an inspection image, an image distortion correction unit that corrects the inspection image and/or the reference image using an estimated distortion amount, and an inspection unit that performs inspection using a corrected inspection image and the reference image or the inspection image and a corrected reference image. The image distortion estimation unit estimates a distortion amount in which only distortion occurring in an entire image can be corrected by adjustment of a correction condition.

Abstract: Provided are a defect inspection apparatus and a defect inspection method that can inspect various types of defects in a synthesized image. The defect inspection apparatus synthesizes a first detection signal from a first detector and a second detection signal from a second detector with a first synthesis ratio to generate a first synthesized image, and synthesizes the first detection signal and the second detection signal with a second synthesis ratio different from the first synthesis ratio to generate a second synthesized image. The defect inspection apparatus generates a first inspection image based on the first synthesized image and generates a second inspection image based on the second synthesized image. The defect inspection apparatus executes a logical operation on the first inspection image and the second inspection image to generate a synthesized inspection image. The defect inspection apparatus executes defect determination on the synthesized inspection image.

Abstract: This invention is directed to a pattern height information correction system which includes a contour line information of a pattern extracted from an acquired image including at least an AFM (atomic force microscope) module, a design information database that stores design information including at least layer information, and a computer system that divides the extracted pattern into regions based on the design information stored in the design information database relating to the extracted pattern and associates the divided regions with layer information, in which the computer system specifies a horizontal region designated as horizontal in advance from the divided regions, creates an approximated curved surface based on the specified horizontal region corresponding to the same layer information, and corrects height information of the extracted pattern using the approximated curved surface.

Abstract: An object of the present invention is to achieve both suppression of data amount of an image processing system that learns a collation image to be used for image identification using a discriminator and improvement of identification performance of the discriminator. In order to achieve the above object, there is proposed an image processing system including a discriminator that identifies an image using a collation image, the image processing system further including a machine learning engine that performs machine learning of collation image data required for image identification. The machine learning engine searches for a successfully identified image using an image for which identification has been failed, and adds information, obtained based on a partial image of the image for which identification has been failed and which has been selected by an input device to the successfully identified image obtained by the search to generate corrected collation image data.

Abstract: A pattern inspection system inspects an image of an inspection target pattern of an electronic device using an identifier constituted by machine learning, based on the image of the inspection target pattern of the electronic device and data used to manufacture the inspection target pattern. The system includes a storage unit which stores a plurality of pattern images of the electronic device and pattern data used to manufacture a pattern of the electronic device, and an image selection unit which selects a learning pattern image used in the machine learning from the plurality of pattern images, based on the pattern data and the pattern image stored in the storage unit.

Abstract: In order to select an optimal learning model for an image when inference is carried out in the extraction of a profile line using machine learning, without requiring a correct value or degree of certainty, a feature extraction learning model group containing a plurality of learning models is used for feature extraction. A recall learning model group containing recall learning models is paired with the feature extraction learning models. A feature amount extraction unit for referencing a feature extraction learning model and extracting a feature amount from input data; a data-to-data recall unit for referencing a recall learning model and outputting a recall result with the feature amount subjected to dimensional compression; and a learning model selection unit for selecting a feature extraction learning model from the feature extraction learning model group under the condition that the difference between the feature amount and the recall result is minimized are provided.

Abstract: An object of the present invention is to achieve both suppression of data amount of an image processing system that learns a collation image to be used for image identification using a discriminator and improvement of identification performance of the discriminator. In order to achieve the above object, there is proposed an image processing system including a discriminator that identifies an image using a collation image, the image processing system further including a machine learning engine that performs machine learning of collation image data required for image identification. The machine learning engine searches for a successfully identified image using an image for which identification has been failed, and adds information, obtained based on a partial image of the image for which identification has been failed and which has been selected by an input device to the successfully identified image obtained by the search to generate corrected collation image data.