Title:
IMAGE RESTORATION MACHINE LEARNING ALGORITHM USING COMPRESSION PARAMETER, AND IMAGE RESTORATION METHOD USING SAME
Document Type and Number:
WIPO Patent Application WO/2018/199459
Kind Code:
A1
Abstract:
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.
More Like This:
Inventors:
KANG HYUN-IN (KR)
KANG JI-HONG (KR)
KANG JI-HONG (KR)
Application Number:
PCT/KR2018/002470
Publication Date:
November 01, 2018
Filing Date:
February 28, 2018
Export Citation:
Assignee:
KANG HYUN IN (KR)
International Classes:
H04N19/136; G06N5/04; G06N99/00; H04N19/124; H04N19/176; H04N19/80; H04N19/86
Foreign References:
| JP2010514246A | 2010-04-30 | |||
| KR20120036847A | 2012-04-18 | |||
| KR20130030254A | 2013-03-26 | |||
| KR20130085838A | 2013-07-30 | |||
| KR20120034042A | 2012-04-09 |
Attorney, Agent or Firm:
LIM, Pyoung-Sup (KR)
Download PDF: