南方科技大学知识苑(SUSTech KC): 眼科多模态影像的检索方法、装置、服务器及存储介质

Title	眼科多模态影像的检索方法、装置、服务器及存储介质
Alternative Title	Ophthalmological multi-modal image retrieval method and device, server and storage medium
Author	方建生; 刘江
First Inventor	方建生
Original applicant	南方科技大学
First applicant	南方科技大学
Address of First applicant	518000 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	518000 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	518000 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	CN202010242450.7
Application Date	2020-03-31
Open (Notice) Number	CN111428072A
Date Available	2020-07-17
Status of Patent	实质审查
Legal Date	2020-08-11
Subtype	发明申请
SUSTech Authorship	First
Abstract	本发明实施例公开了一种眼科多模态影像的检索方法、装置、服务器及存储介质，该方法包括：获取用户当前的眼部图像，所述眼部图像为眼科数字影像，所述眼部图像包含多种不同模态的眼部影像；将所述多种不同模态的眼部影像对应输入到多个预先训练好的深度学习模型融合训练所述多种不同模态的眼部影像的相似性和不相似性并输出多个特征向量，根据所述多个特征向量生成对比分析结果。通过获取用户的单模态眼睛图像，系统在深度学习模型中进行识别，输出多模态识别结果，解决了现有技术中无法通过单模态眼部图像发现用户其他潜在眼部疾病的问题，实现了通过单模态眼部图像检索到其他可能存在的眼部疾病的效果，提升了用户的体验。
Other Abstract	The embodiment of the invention discloses an ophthalmic multi-modal image retrieval method and device, a server and a storage medium, and the method comprises the steps of obtaining a current eye image of a user, enabling the eye image to be an ophthalmic digital image, and enabling the eye image to comprise various eye images in different modes; and correspondingly inputting the eye images of thedifferent modes into a plurality of pre-trained deep learning models to perform fusion training on the similarity and dissimilarity of the eye images of the different modes, outputting a plurality offeature vectors, and generating a comparative analysis result according to the feature vectors. A single-mode eye image of a user is obtained; the system performs recognition in the deep learning model and outputs a multi-modal recognition result, so that the problem that other potential eye diseases of a user cannot be found through a single-modal eye image in the prior art is solved, the effectof retrieving other possible eye diseases through the single-modal eye image is achieved, and the user experience is improved.
CPC Classification Number	G06F16/583 ; G06F16/55 ; G06V40/193 ; G06V40/197 ; G06V2201/03 ; G06N3/045 ; G06F18/22 ; G06F18/25 ; G06F18/241
IPC Classification Number	G06F16/583 ; G06F16/55 ; G06K9/00 ; G06K9/62 ; G06N3/04
INPADOC Legal Status	（ENTRY INTO FORCE OF REQUEST FOR SUBSTANTIVE EXAMINATION）[2020-08-11][CN]
INPADOC Patent Family Count	1
Extended Patent Family Count	1
Priority date	2020-03-31
Patent Agent	孟金喆 ; 潘登
Agency	北京品源专利代理有限公司
URL	[Source Record]
Data Source	PatSnap
Document Type	Patent
Identifier	http://kc.sustech.edu.cn/handle/2SGJ60CL/534264
Department	Department of Computer Science and Engineering
Recommended Citation GB/T 7714	方建生,刘江. 眼科多模态影像的检索方法、装置、服务器及存储介质.

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