Image region segmentation model training method and device, and image region segmentation method and device

An image area and segmentation model technology, applied in the field of artificial intelligence, can solve the problems of weak supervision signal, difficulty in accurately segmenting target areas, weak supervision, etc., to achieve the effect of improving accuracy

Active Publication Date: 2020-08-28
腾讯医疗健康(深圳)有限公司
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to the weak supervision with image-level labels, the supervision signal is too weak, and it is difficult to accurately segment the target region of interest.

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 region segmentation model training method and device, and image region segmentation method and device
  • Image region segmentation model training method and device, and image region segmentation method and device
  • Image region segmentation model training method and device, and image region segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Embodiments of the present application are described below in conjunction with the accompanying drawings.

[0047]Deep learning has been widely used in the field of segmentation, but in order to train a good image region segmentation model, accurate pixel-level mask is often required, but pixel-level manual labeling is extremely time-consuming and labor-intensive. For example, it usually takes 5-30 minutes to manually mark the cancer area in a 2048*2048 case picture. Therefore, generating a large number of annotated sample images becomes very expensive and time-consuming. In view of this, it was born based on the application of Weaklysupervised segmentation method. The weak supervision algorithm may be, for example, a class activation mapping (Class Activation Mapping, CAM) algorithm.

[0048] The weakly supervised methods in related technologies usually use image-level labels (often image categories) related to segmentation tasks to train classification models, and u...

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 embodiment of the invention discloses an image region segmentation model training method and device based on artificial intelligence, and an image region segmentation method and device based on artificial intelligence. In the model training process, a sample image set comprising at least one sample image is acquired, wherein the sample image has first annotation information, and the first annotation information can be annotation information with large granularity such as an image level. For each sample image in the sample image set, graph structure data corresponding to the sample image isgenerated, and each vertex in the graph structure data comprises at least one pixel point in the sample image. Second annotation information of the vertex is determined according to the graph structure data and the first annotation information through a graph convolution network model, wherein the granularity of the second annotation information is smaller than the granularity of the first annotation information. Since the vertexes are actually superpixel points and the second annotation information is superpixel-level annotation, in the training process, due to intervention of pixel-level annotation, strong supervision can be achieved, and the accuracy of the model is improved, and then the accuracy of image segmentation is improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to an artificial intelligence-based image region segmentation model training method, segmentation method and device. Background technique [0002] With the development of computer technology, image segmentation technology is more and more widely used, for example, medical image segmentation and natural image segmentation. Among them, image segmentation technology refers to the technology of dividing the image into several specific regions with unique properties and proposing the target of interest. For example, in the medical image segmentation scenario, the cancer region of the medical image can be segmented for further analysis. [0003] Deep learning has been widely used in the field of image region segmentation. In order to reduce the time and labor cost of generating a large number of annotated images, related technologies adopt image-level annotation and use w...

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): G06T7/11G06N3/04G06N3/08
CPCG06T7/11G06N3/08G06T2207/20081G06N3/045G06T7/194G06T2207/20084G06T7/162G06V10/82G06V20/695G06V10/7747
Inventor 张军田宽颜克洲姚建华韩骁
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