南方科技大学知识苑(SUSTech KC): 图像修复方法、电子设备及存储介质

Title	图像修复方法、电子设备及存储介质
Alternative Title	Image restoration method, electronic equipment and storage medium
Author	曾媛; 贡毅
First Inventor	曾媛
Original applicant	南方科技大学
First applicant	南方科技大学
Address of First applicant	518055 广东省深圳市南山区西丽学苑大道1088号
Current applicant	南方科技大学
Address of Current applicant	518055 广东省深圳市南山区西丽学苑大道1088号 (广东,深圳,南山区)
First Current Applicant	南方科技大学
Address of First Current Applicant	518055 广东省深圳市南山区西丽学苑大道1088号 (广东,深圳,南山区)
Application Number	CN202110896496.5
Application Date	2021-08-05
Open (Notice) Number	CN113744142A
Date Available	2021-12-03
Status of Patent	实质审查
Legal Date	2021-12-21
Subtype	发明申请
SUSTech Authorship	First
Abstract	本申请公开了一种图像修复方法、电子设备及存储介质，涉及图像处理技术领域。本申请的图像修复方法，包括：获取待修复图像，对待修复图像进行边缘检测，得到边缘图像，对得到的边缘图像的结构线条进行修复，得到初步修复图像，对初步修复图像进行处理，得到多个尺寸的初步图像数据，对初步图像数据的纹理色彩进行修复，得到目标图像，本申请通过设计基于图像的结构线条完整和纹理色彩填充两步骤的待修复图像的修复框架、定义图像修复的优先秩序，并且基于多个尺寸的图像进行图像修复，能够考虑图像的全局特征，有效捕捉图像的全局语义定义，从而提高图像修复准确度。
Other Abstract	The invention discloses an image restoration method, electronic equipment and a storage medium, and relates to the technical field of image processing. The image restoration method comprises the following steps of: obtaining a to-be-restored image; carrying out edge detection on the to-be-restored image to obtain an edge image; restoring a structure line of the obtained edge image to obtain a preliminarily restored image; processing the preliminarily restored image to obtain preliminary image data of multiple sizes; and restoring the texture color of the preliminary image data to obtain a target image. According to the image restoration method, a restoration framework of the to-be-restored image based on the two steps of image structure line integrity and texture color filling is designed, the priority order of image restoration is defined, image restoration is performed based on images of multiple sizes, the global features of the image can be considered, the global semantic definition of the image is effectively captured, and therefore, the image restoration accuracy is improved.
CPC Classification Number	G06T5/005 ; G06T7/13 ; G06N3/08 ; G06T2207/20081 ; G06T2207/20084 ; G06N3/045
IPC Classification Number	G06T5/00 ; G06T7/13 ; G06N3/04 ; G06N3/08
INPADOC Legal Status	（ENTRY INTO FORCE OF REQUEST FOR SUBSTANTIVE EXAMINATION）[2021-12-21][CN]
INPADOC Patent Family Count	1
Extended Patent Family Count	1
Priority date	2021-08-05
Patent Agent	廖慧贤
Agency	广州嘉权专利商标事务所有限公司
URL	[Source Record]
Data Source	PatSnap
Document Type	Patent
Identifier	http://kc.sustech.edu.cn/handle/2SGJ60CL/533642
Department	Research Institute of Trustworthy Autonomous Systems 工学院
Recommended Citation GB/T 7714	曾媛,贡毅. 图像修复方法、电子设备及存储介质.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation Sequential No:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh