公开(公告)号：US20190197673A1

公开(公告)日：2019-06-27

申请号：US16232711

申请日：2018-12-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaeho JUNG ,  Yeultak SUNG

IPC: G06T5/50 ,  G06T7/246

CPC classification number: G06T5/50 ,  G06T7/248 ,  G06T2207/20084

Abstract: Provided is an artificial intelligence (AI) system that mimics functions, such as recognition and determination by human brains, by utilizing a machine learning algorithm, such as deep learning, and applications of the AI system. An image acquisition device is disclosed including a camera configured to acquire a first image, wherein a portion of a main object is hidden from the camera by a sub-object; at least one processor configured to input the first image to a first AI neural network; detect, by the first AI neural network from data corresponding to a plurality of objects included in the first image, first data corresponding to the main object and second data corresponding to the sub-object from the first image by inputting the first image to an AI neural network, remove the sub-object from the first image, and generate, using a second AI neural network, a second image by restoring third data corresponding to at least a portion of the main object hidden by the removed sub-object by using the AI neural network, wherein the third data replaces the second data; and a display configured to display at least one of the first image and the second image.

公开(公告)号：US20240037712A1

公开(公告)日：2024-02-01

申请号：US18484979

申请日：2023-10-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaeho JUNG ,  Yeultak SUNG

IPC: G06T5/50 ,  G06T7/246 ,  G06T5/00

CPC classification number: G06T5/50 ,  G06T7/248 ,  G06T5/005 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/20221

Abstract: Provided is an artificial intelligence (AI) system that mimics functions, such as recognition and determination by human brains, by utilizing a machine learning algorithm, such as deep learning, and applications of the AI system. An image acquisition device is disclosed including a camera configured to acquire a first image, wherein a portion of a main object is hidden from the camera by a sub-object; at least one processor configured to input the first image to a first AI neural network; detect, by the first AI neural network from data corresponding to a plurality of objects included in the first image, first data corresponding to the main object and second data corresponding to the sub-object from the first image by inputting the first image to an AI neural network, remove the sub-object from the first image, and generate, using a second AI neural network, a second image by restoring third data corresponding to at least a portion of the main object hidden by the removed sub-object by using the AI neural network, wherein the third data replaces the second data; and a display configured to display at least one of the first image and the second image.

公开(公告)号：US20220245779A1

公开(公告)日：2022-08-04

申请号：US17728535

申请日：2022-04-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaeho JUNG ,  Yeultak SUNG

IPC: G06T5/50 ,  G06T7/246 ,  G06T5/00

Abstract: Provided is an artificial intelligence (AI) system that mimics functions, such as recognition and determination by human brains, by utilizing a machine learning algorithm, such as deep learning, and applications of the AI system. An image acquisition device is disclosed including a camera configured to acquire a first image, wherein a portion of a main object is hidden from the camera by a sub-object; at least one processor configured to input the first image to a first AI neural network; detect, by the first AI neural network from data corresponding to a plurality of objects included in the first image, first data corresponding to the main object and second data corresponding to the sub-object from the first image by inputting the first image to an AI neural network, remove the sub-object from the first image, and generate, using a second AI neural network, a second image by restoring third data corresponding to at least a portion of the main object hidden by the removed sub-object by using the AI neural network, wherein the third data replaces the second data; and a display configured to display at least one of the first image and the second image.