Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2018199459) IMAGE RESTORATION MACHINE LEARNING ALGORITHM USING COMPRESSION PARAMETER, AND IMAGE RESTORATION METHOD USING SAME
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2018/199459 International Application No.: PCT/KR2018/002470
Publication Date: 01.11.2018 International Filing Date: 28.02.2018
IPC:
H04N 19/136 (2014.01) ,H04N 19/124 (2014.01) ,H04N 19/80 (2014.01) ,H04N 19/86 (2014.01) ,H04N 19/176 (2014.01) ,G06N 5/04 (2006.01) ,G06N 99/00 (2010.01)
[IPC code unknown for H04N 19/136][IPC code unknown for H04N 19/124][IPC code unknown for H04N 19/80][IPC code unknown for H04N 19/86][IPC code unknown for H04N 19/176]
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5
Computer systems utilizing knowledge based models
04
Inference methods or devices
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99
Subject matter not provided for in other groups of this subclass
Applicants:
강현인 KANG, Hyun-In [KR/KR]; KR
Inventors:
강현인 KANG, Hyun-In; KR
강지홍 KANG, Ji-Hong; KR
Agent:
임평섭 LIM, Pyoung-Sup; KR
Priority Data:
10-2017-005328426.04.2017KR
Title (EN) IMAGE RESTORATION MACHINE LEARNING ALGORITHM USING COMPRESSION PARAMETER, AND IMAGE RESTORATION METHOD USING SAME
(FR) ALGORITHME D'APPRENTISSAGE AUTOMATIQUE DE RESTAURATION D'IMAGE UTILISANT UN PARAMÈTRE DE COMPRESSION, ET PROCÉDÉ DE RESTAURATION D'IMAGE L'UTILISANT
(KO) 압축 파라미터를 이용한 영상 복원용 머신러닝 알고리즘 및 이를 이용한 영상 복원방법
Abstract:
(EN) The objective of the present invention is to provide a machine learning algorithm and an image restoration method using the same, the algorithm and the method: making compression information and deterioration images into input data; being configured such that an optimal model corresponding to a variety of compression information is learned and derived by itself by using a machine learning algorithm aimed at restoration of an original image, thereby enabling image restorability and compression ratio to be remarkably improved by applying the optimal model corresponding to the compression information during image restoration; and, in configuring a loss function which is a function for obtaining a difference value between the restored image and the original image during learning, assigning different weights according to the compression information, thereby enabling image restoration for a specific region to be precisely performed.
(FR) La présente invention vise à fournir un algorithme d'apprentissage automatique et un procédé de restauration d'image l'utilisant, l'algorithme et le procédé consistant à : transformer des informations de compression et des images de détérioration en des données d'entrée ; étant configuré de sorte qu'un modèle optimal correspondant à une variété d'informations de compression soit appris et déduit de lui-même à l'aide d'un algorithme d'apprentissage automatique visant à restaurer une image d'origine, ce qui permet d'améliorer considérablement la capacité de restauration d'image et le taux de compression en appliquant le modèle optimal correspondant aux informations de compression pendant la restauration d'image ; et, configurer une fonction de perte qui constitue une fonction permettant d'obtenir une valeur de différence entre l'image restaurée et l'image d'origine pendant l'apprentissage, attribuer différents poids selon les informations de compression, ce qui permet une restauration d'image pour une région spécifique.
(KO) 본 발명은 압축정보 및 열화 영상을 입력데이터로 하며, 원본 영상으로의 복원을 목표로 하는 머신러닝 알고리즘을 이용하여 다양한 압축정보에 대응되는 최적의 모델을 스스로 학습하여 도출하도록 구성됨으로써 영상 복원 시 압축정보에 대응되는 최적의 모델을 적용하여 영상 복원력 및 압축률을 현저히 개선시킬 수 있고, 학습 시 복원된 영상과 원본 영상의 차이값을 구하기 위한 함수인 loss function을 구성하는데 있어서, 압축정보에 따라 서로 다른 가중치를 부여함으로써 특정영역에 대한 영상복원을 정밀하게 수행할 수 있는 머신러닝 알고리즘 및 이를 이용한 영상 복원방법을 제공하기 위한 것이다.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: Korean (KO)
Filing Language: Korean (KO)