公开(公告)号：US20220414833A1

公开(公告)日：2022-12-29

申请号：US17749331

申请日：2022-05-20

Applicant: Hitachi High-Tech Corporation

Inventor： Kosuke FUKUDA ,  Masayoshi ISHIKAWA ,  Yasuhiro YOSHIDA ,  Hiroyuki SHINDO

IPC: G06T5/00 ,  G06T7/00 ,  G06T3/40 ,  G06T7/62

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.

公开(公告)号：US20240362892A1

公开(公告)日：2024-10-31

申请号：US18580712

申请日：2021-07-30

Applicant: Hitachi High-Tech Corporation

Inventor： Sota KOMATSU ,  Masayoshi ISHIKAWA ,  Fumihiro BEKKU

IPC: G06V10/764 ,  G06T3/40 ,  G06V10/44 ,  G06V10/762 ,  G06V10/771

CPC classification number: G06V10/764 ,  G06T3/40 ,  G06V10/44 ,  G06V10/762 ,  G06V10/771

Abstract: Provided are an image classification device and method that are capable of extracting and mapping an important feature in an image. The image classification device includes: a feature extraction unit 101 that generates a first image group generated by applying different noises to the same image among images included in an image group and a second image group including different images, is trained such that features obtained from the first image group are approximate, is trained such that features obtained from the second image group are more different, and extracts features; a feature mapping unit 102 that maps the extracted plurality of features two-dimensionally or three-dimensionally using manifold learning; and a display unit 103 that displays a mapping result and constructs a training information application task screen.

公开(公告)号：US20230325413A1

公开(公告)日：2023-10-12

申请号：US18024930

申请日：2020-09-17

Applicant: Hitachi High-Tech Corporation

Inventor： Yasuhiro YOSHIDA ,  Masayoshi ISHIKAWA ,  Fumihiro SASAJIMA ,  Masami TAKANO ,  Koichi HAYAKAWA

IPC: G06F16/28 ,  G06F16/22

CPC classification number: G06F16/285 ,  G06F16/2246

Abstract: An error cause estimation device comprising: a data pre-processing unit that uses data to be processed and generates training data that has an appropriate format for input to a machine learning model; and a model tree generation unit that generates error detection models that are training models for detecting errors and uses the training data as inputs therefor, and generates a model tree that expresses the relationship between error detection models by using a tree structure that has the error detection models as node therefor. Thus, it is possible to generate a training model that detects errors for each of a plurality of types of errors that occur, even when there has been no prior annotation of error causes.

公开(公告)号：US20230095532A1

公开(公告)日：2023-03-30

申请号：US17907921

申请日：2020-03-30

Applicant: Hitachi High-Tech Corporation

Inventor： Fumihiro SASAJIMA ,  Masami TAKANO ,  Kazuhiro UEDA ,  Masayoshi ISHIKAWA ,  Yasuhiro YOSHIDA

IPC: G05B23/02

Abstract: The present disclosure proposes a diagnostic system capable of properly identifying the cause of even an error for which multiple factors or multiple compound factors may be accountable. The diagnostic system according to the present disclosure is provided with a learning device for learning at least one of a recipe defining operations of an inspection device, log data describing states of the device, or specimen data describing characteristics of a specimen in association with error types of the device, and estimates the cause of the error by using the learning device (refer to FIG. 4).

公开(公告)号：US20230077332A1

公开(公告)日：2023-03-16

申请号：US17895264

申请日：2022-08-25

Applicant: Hitachi High-Tech Corporation

Inventor： Yuko SANO ,  Masayoshi ISHIKAWA ,  Hiroyuki SHINDO

IPC: G06T7/00 ,  G01N21/95 ,  G06T7/70 ,  G06V10/764 ,  G06V10/22 ,  G06V10/774 ,  G06V10/82

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.

公开(公告)号：US20220334172A1

公开(公告)日：2022-10-20

申请号：US17634809

申请日：2019-09-06

Applicant: Hitachi High-Tech Corporation

Inventor： Kouichi HAYAKAWA ,  Masami TAKANO ,  Kazuhiro UEDA ,  Masayoshi ISHIKAWA ,  Yasuhiro YOSHIDA

IPC: G01R31/28 ,  H01L21/66

Abstract: An objective of the present invention is to provide a system which can infer the cause of a recipe error and present a correction candidate for the recipe error. A recipe information presentation system or recipe error inference system according to the present invention: causes a learner to learn a correspondence between a recipe and an error originating from the recipe; and acquires from the learner an inference result as to whether the error occurs when a new recipe is used (refer to FIG. 1).

公开(公告)号：US20240403183A1

公开(公告)日：2024-12-05

申请号：US18698452

申请日：2021-10-29

Applicant: Hitachi High-Tech Corporation

Inventor： Yasuhiro YOSHIDA ,  Masayoshi ISHIKAWA ,  Fumihiro SASAJIMA ,  Shigeo OKOSHI

IPC: G06F11/32 ,  G06F11/30

Abstract: This error factor estimation device 100 is a device for estimating the error factor of errors that occur, and comprises: a feature-quantity-group-generating unit A2a that processes data including inspection results collected from an inspection device and generates a plurality of feature quantities; a model-generating unit 4 that generates a model A5a for learning the relationship between the plurality of feature quantities generated by the feature-quantity-group-generating unit A2a and errors; a contribution-degree-calculating unit 11 that calculates a contribution degree indicating the degree of contribution to the output of the model A5a for at least one of the plurality of feature quantities used for the model A5a learning; and an error factor acquisition unit 15 that acquires error factors labeled with feature quantities selected on the basis of the usefulness calculated from the contribution degree calculated by the contribution-degree-calculating unit 11.

公开(公告)号：US20230222764A1

公开(公告)日：2023-07-13

申请号：US18009890

申请日：2020-06-16

Applicant: Hitachi High-Tech Corporation

Inventor： Masanori OUCHI ,  Masayoshi ISHIKAWA ,  Yasutaka TOYODA ,  Hiroyuki SHINDO

IPC: G06V10/75 ,  G06T7/00 ,  G06V10/74

CPC classification number: G06V10/751 ,  G06T7/0006 ,  G06V10/758 ,  G06V10/761 ,  G06T2207/30148

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.

公开(公告)号：US20220415024A1

公开(公告)日：2022-12-29

申请号：US17781295

申请日：2020-01-09

Applicant: Hitachi High-Tech Corporation

Inventor： Yasutaka TOYODA ,  Masayoshi ISHIKAWA ,  Masanori OUCHI

IPC: G06V10/776 ,  G06T7/11 ,  G06V10/774 ,  G06V10/98 ,  G06T5/50

Abstract: This disclosure relates to a system for performing efficient learning of a specific portion. To achieve this purpose, there is proposed a system configured to generate a converted image on the basis of input of an input image, the system comprising a learning model in which parameters are adjusted so as to suppress an error between the input image and a second image converted upon input of the input image, the learning model being subjected to different learning at least between a first area in the image and a second area different from the first area.

公开(公告)号：US20220374785A1

公开(公告)日：2022-11-24

申请号：US17734667

申请日：2022-05-02

Applicant: Hitachi High-Tech Corporation

Inventor： Masayoshi ISHIKAWA ,  Sota KOMATSU ,  Yuichi ABE ,  Mitsuji IKEDA

IPC: G06N20/20 ,  G06K9/62

Abstract: A machine learning system performs transfer learning to output a trained model by performing training using a parameter of a pre-trained model by using a given dataset and a given pre-trained model. The machine learning system includes a dataset storage unit that stores one or more datasets, and a first training unit that performs training using a dataset stored in the dataset storage unit to generate the pre-trained model, and stores the generated pre-trained model in a pre-trained model database. The dataset storage unit stores tag information including any one or more of domain information indicating a target object of data included in a dataset to be stored, class information indicating a class included in data, and data acquisition condition information related to an acquisition condition of data and a dataset in a manner that the tag information and the dataset are associated with each other.