Image recognition model training and image recognition method, device and system

A technology of image recognition and model training, applied in the computer field, can solve the problems of single labeling of samples and low accuracy of lesion prediction

Active Publication Date: 2019-07-12
腾讯医疗健康(深圳)有限公司
View PDF7 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides an image recognition model training and image recognition method, device and system to solve the problem in the prior art that the sample labeling is single, which leads to the low accuracy of the trained model in predicting lesions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image recognition model training and image recognition method, device and system
  • Image recognition model training and image recognition method, device and system
  • Image recognition model training and image recognition method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0102] The first embodiment: the training image sample set only includes strong-label training image samples, then based on the image feature information of the image samples and the corresponding strong label information, mark the image feature information belonging to each preset lesion category, and according to the marking results, The image recognition model is trained until the strongly supervised objective function of the image recognition model converges, and the trained image recognition model is obtained.

[0103] It specifically includes: S1. According to the image feature information of the image sample and the corresponding strong label information, mark the image feature information belonging to each preset lesion category, and determine the strong supervision objective function according to the marking result.

[0104] In the embodiment of the present invention, when training based on strong-label training image samples, the input of the image recognition model i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of computers, in particular to an image recognition model training and image recognition method, device and system, and the method comprises the steps: obtaining a training image sample set which at least comprises strong label training image samples, wherein the strong label training image sample represents an image sample with strong label information, and the strong label information at least comprises the lesion category and the labeling information of the lesion position; extracting image feature information of image samples in the training image sample set; based on the image feature information and the corresponding strong label information, marking the image feature information belonging to each preset lesion category, and training an image recognition model according to the marking result until the strong supervision objective function converges to obtain a trained image recognition model, thereby obtaining a lesion category recognition result of the to-be-recognized image based on the image recognition model. The image feature information of a certain lesion category can be positioned more accurately according to the lesion position, noise is reduced, and reliability and accuracy are improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an image recognition model training and image recognition method, device and system. Background technique [0002] For various medical imaging diagnostic analysis, for example, the diagnosis of digestive tract diseases is usually based on diagnostic tools such as endoscopy. After obtaining the internal image of the body, relevant medical personnel can judge whether there is a lesion and the type of the lesion by human eye observation. The recognition efficiency is low. [0003] In the prior art, a recognition method is also provided, which is mainly to obtain a large number of endoscopic images, and the relevant medical personnel will mark each image with a lesion category, and use the marked images as samples for model training, so that based on the training The model is used to identify lesions on other medical images, judge whether lesions occur, and automatically give the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/0012G06T2207/20081G06T2207/20084G06T2207/30096G06T2207/10068G06T2207/30092G06T2207/30028G16H50/20G16H30/40G16H50/70G06N3/08G06N3/048G06N3/045
Inventor 郑瀚孙钟前尚鸿付星辉杨巍
Owner 腾讯医疗健康(深圳)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap