Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 9:00 AM CET
Settings

Settings

Goto Application

1. WO2021230624 - IMAGE PROCESSING DEVICE AND OPERATION METHOD THEREOF

Publication Number WO/2021/230624
Publication Date 18.11.2021
International Application No. PCT/KR2021/005888
International Filing Date 11.05.2021
IPC
H04N 19/86 2014.1
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
85using pre-processing or post-processing specially adapted for video compression
86involving reduction of coding artifacts, e.g. of blockiness
H04N 19/82 2014.1
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
80Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
82involving filtering within a prediction loop
G06T 9/00 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
9Image coding
G06N 3/08 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06T 9/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
9Image coding
H04N 19/82
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
80Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
82involving filtering within a prediction loop
H04N 19/86
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
85using pre-processing or post-processing specially adapted for video compression
86involving reduction of coding artifacts, e.g. of blockiness
Applicants
  • 삼성전자 주식회사 SAMSUNG ELECTRONICS CO., LTD. [KR]/[KR]
Inventors
  • 안일준 AHN, Iljun
  • 이태미 LEE, Tammy
  • 강수민 KANG, Soomin
  • 박재연 PARK, Jaeyeon
Agents
  • 리앤목특허법인 Y.P.LEE, MOCK & PARTNERS
Priority Data
10-2020-005833315.05.2020KR
10-2020-015910024.11.2020KR
Publication Language Korean (ko)
Filing Language Korean (KO)
Designated States
Title
(EN) IMAGE PROCESSING DEVICE AND OPERATION METHOD THEREOF
(FR) DISPOSITIF DE TRAITEMENT D'IMAGE ET PROCÉDÉ DE COMMANDE ASSOCIÉ
(KO) 영상 처리 장치 및 그 동작방법
Abstract
(EN) Disclosed is an image processing device comprising a memory which stores one or more instructions, and a processor which executes the one or more instructions stored in the memory, wherein the processor: extracts n pieces of first feature information from a first image on the basis of the positions of pixels included in the first image by using one or more neural networks; performs a convolution operation between the n pieces of first feature information and n kernels so as to generate n pieces of second feature information; and generates a second image on the basis of the n pieces of second feature information, and the second image is obtained by removing a compression artifact included in the first image.
(FR) L'invention concerne un dispositif de traitement d'image comprenant une mémoire qui stocke une ou plusieurs instructions, et un processeur qui exécute la ou les instructions stockées dans la mémoire. Le processeur : extrait n éléments de premières informations caractéristiques à partir d'une première image sur la base des positions de pixels inclus dans la première image en utilisant un ou plusieurs réseaux neuronaux; effectue une opération de convolution entre les n éléments de premières informations caractéristiques et n noyaux de sorte à générer n éléments de secondes informations caractéristiques; et génère une seconde image sur la base des n éléments de secondes informations caractéristiques, et la seconde image est obtenue en éliminant un artefact de compression inclus dans la première image.
(KO) 영상 처리 장치에 관한 것으로, 하나 이상의 인스트럭션들을 저장하는 메모리, 및 메모리에 저장된 상기 하나 이상의 인스트럭션들을 실행하는 프로세서를 포함하고, 프로세서는, 하나 이상의 뉴럴 네트워크를 이용하여, 제1 영상에 포함되는 픽셀들의 위치에 기초하여, 제1 영상으로부터 n개의 제1 특징 정보들을 추출하고, n개의 제1 특징 정보들 각각과 n개의 커널들 각각과의 컨볼루션 연산을 수행함으로써, n개의 제2 특징 정보들을 생성하며, n개의 제2 특징 정보들에 기초하여, 제2 영상을 생성하고, 제2 영상은 제1 영상에 포함되는 압축 아티팩트가 제거된 영상인, 영상 처리 장치가 개시된다.
Latest bibliographic data on file with the International Bureau