-
公开(公告)号：US20250140516A1
公开(公告)日：2025-05-01
申请号：US18865765
申请日：2022-05-30
Applicant: Hitachi High-Tech Corporation
Inventor： Hiromi FUJITA , Toshikazu KAWAHARA , Hitoshi SUGAHARA
Abstract: According to the present invention, a design image based on design data is set for each image acquisition condition, and a length measurement cursor is set in each of the design images. This recipe creating system for creating a recipe in which a procedure for measuring the length of an observed object is described, involves executing: a storage process of storing design data of an observed object including a plurality of layers; a layer-setting process of setting, from among the plurality of layers, at least one layer for each image acquisition condition for the observed object; and a length measurement cursor-setting process of setting a length measurement cursor indicating a length measurement region of the observed object in a design image formed by a design present in the at least one layer set in the setting process.
-
公开(公告)号：US20220036116A1
公开(公告)日：2022-02-03
申请号：US17503438
申请日：2021-10-18
Applicant: Hitachi High-Tech Corporation
Inventor： Shinichi SHINODA , Yasutaka TOYODA , Shigetoshi SAKIMURA , Masayoshi ISHIKAWA , Hiroyuki SHINDO , Hitoshi SUGAHARA
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.
-
公开(公告)号：US20210043418A1
公开(公告)日：2021-02-11
申请号：US16891842
申请日：2020-06-03
Applicant: Hitachi High-Tech Corporation
Inventor： Chikako ABE , Hitoshi SUGAHARA
IPC: H01J37/28 , H01J37/26 , H01J37/244 , G06N20/00
Abstract: The present invention relates to an image generation method for an objective for generating an image corresponding to a multi-frame image from image signals obtained by scanning a small number of frames are proposed. To achieve the above objective, there is proposed a method of performing two-dimensionally scanning on an object on a sample with a beam a plurality of times, generating a first image by integrating image signals obtained by a plurality of times of scanning at a first timing among the image signals generated based on the plurality of times of the two-dimensional scanning (S103), generating a second image based on the smaller number of times of scanning than the number of times of scanning at the first timing including scanning after the first timing (S105), training a learning device by using teacher data with the second image as an input and the first image as an output (S108), and inputting input image signals obtained by the smaller number of times of scanning than the number of times of scanning at the first timing to the trained learning device to output an estimated image.
-
-
Search Results
3
records
(took 0.012 seconds)
