公开(公告)号：US12205040B2

公开(公告)日：2025-01-21

申请号：US17245173

申请日：2021-04-30

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yoonsung Bae ,  Seungho Gwak ,  Kwangrak Kim ,  Seunggun Byoun ,  Gilwoo Song ,  Younghoon Shin ,  Kyungwon Yun ,  Chiyoung Lee ,  Taeyong Jo

IPC: G06N3/088 ,  G06N3/042 ,  G06N3/045 ,  G06N3/067 ,  H01L21/66

Abstract: A method of manufacturing a semiconductor device includes forming a pattern on a wafer, measuring a spectrum of the pattern on the wafer, with a spectral optical system, performing an analysis of the spectrum through a deep learning model for predicting pattern characteristics, the deep learning model being trained based on a domain knowledge, and evaluating the pattern on the wafer based on the analysis of the spectrum, wherein the domain knowledge includes a noise inducing factor of the spectral optical system.

公开(公告)号：US12067794B2

公开(公告)日：2024-08-20

申请号：US17520245

申请日：2021-11-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehyun Kwon ,  Jinwoo Nam ,  Gilwoo Song ,  Heeseung Shin ,  Minseok Choi

IPC: G06T7/70 ,  G06T7/00 ,  G06V10/764 ,  G06V10/82 ,  G06V20/00 ,  G06V40/16

CPC classification number: G06V20/95 ,  G06T7/0002 ,  G06T7/70 ,  G06V10/764 ,  G06V10/82 ,  G06V40/16 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A server and an electronic device for identifying a fake image are provided. The server includes a memory storing an artificial intelligence model trained to identify a fake image; and a processor connected to the memory, and configured to identify whether an image is the fake image by inputting the image to the artificial intelligence model, wherein the artificial intelligence model is a model trained based on an original image and a sample fake image, each including information about a landmark of a face area.

公开(公告)号：US20220058375A1

公开(公告)日：2022-02-24

申请号：US17520245

申请日：2021-11-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehyun KWON ,  Jinwoo Nam ,  Gilwoo Song ,  Heeseung Shin ,  Minseok Choi

IPC: G06K9/00 ,  G06T7/70 ,  G06T7/00

Abstract: A server and an electronic device for identifying a fake image are provided. The server includes a memory storing an artificial intelligence model trained to identify a fake image; and a processor connected to the memory, and configured to identify whether an image is the fake image by inputting the image to the artificial intelligence model, wherein the artificial intelligence model is a model trained based on an original image and a sample fake image, each including information about a landmark of a face area.

公开(公告)号：US11842274B2

公开(公告)日：2023-12-12

申请号：US17140706

申请日：2021-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gilwoo Song ,  Jaehyun Kwon ,  Jinwoo Nam ,  Heeseung Shin ,  Minseok Choi

IPC: G06N3/00 ,  G06N3/08 ,  G06V20/40 ,  G06F18/22 ,  G06N3/045 ,  G06V10/22 ,  G06V10/25 ,  G06V10/75

CPC classification number: G06N3/08 ,  G06F18/22 ,  G06N3/045 ,  G06V10/22 ,  G06V20/41 ,  G06V20/46 ,  G06V10/25 ,  G06V10/751

Abstract: A controlling method of an electronic apparatus may include: obtaining image data and metadata regarding the image data, the image data comprising a first image frame and a second image frame that is subsequent to the first image frame; obtaining information regarding a region of interest of the first image frame by inputting the first image frame to a first neural network model; obtaining a similarity between the first image frame and the second image frame based on motion vector information included in the metadata; and detecting whether there is a manipulated area in the second image frame based on the similarity.

公开(公告)号：US20210209374A1

公开(公告)日：2021-07-08

申请号：US17140706

申请日：2021-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gilwoo Song ,  Jaehyun Kwon ,  Jinwoo Nam ,  Heeseung Shin ,  Minseok Choi

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/32 ,  G06N3/04 ,  G06N3/08

Abstract: A controlling method of an electronic apparatus may include: obtaining image data and metadata regarding the image data, the image data comprising a first image frame and a second image frame that is subsequent to the first image frame; obtaining information regarding a region of interest of the first image frame by inputting the first image frame to a first neural network model; obtaining a similarity between the first image frame and the second image frame based on motion vector information included in the metadata; and detecting whether there is a manipulated area in the second image frame based on the similarity.