Image segmentation model training method and image segmentation method and device

An image segmentation and model training technology, applied in the field of image processing, can solve the problems of low image segmentation accuracy, low efficiency, and differences in segmentation results, and achieve accurate segmentation results

Active Publication Date: 2019-08-30
BEIJING PEREDOC TECH CO LTD
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when segmenting different images containing different occluded objects, it is necessary to re-divide the occluded areas between different objects, which is less efficient
For example, when performing image segmentation on the lung field area in the chest radiograph image, the existing technology is to design a segmentation method by manually observing the characteristics of the chest radiograph lung field. During image segmentation, it is necessary to manually re-divide the overlapping image areas between the clavicle, heart shadow, and lung field, and then perform image segmentation. However, each person's chest image is different. less efficient
[0003] In the process of image segmentation, due to the method of artificially dividing the occlusion area between objects, it may be subject to the subjective influence of the staff, resulting in that when different staff segment the image after manual division of the occlusion area of ​​the same image, the segmentation results are different. There are differences, and the accuracy of image segmentation is low

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] see figure 1 As shown, it is a schematic flowchart of a method for image segmentation model training provided in the embodiment of the present application, including the following steps:

[0063] Step 101, acquiring a sample image library.

[0064] Specifically, the sample image library contains multiple sets of sample images, each set of sample images includes the sample image and the corresponding tagged image of the sample image, the sample image includes overlapping image regions between different objects, and the tagged image is marked with different The reference boundary area between objects.

[0065] Exemplarily, the sample image may be a chest radiograph image, wherein the chest radiograph image includes overlapping image areas among clavicle, heart shadow and lung field, and the tagged image corresponding to the chest radiograph image is marked with clavicle, heart shadow and lung field The chest radiographic image corresponding to the reference border area,...

Embodiment 2

[0103] This embodiment provides a device for image segmentation model training, such as Figure 4 As shown, it is a schematic structural diagram of an image segmentation model training device 400 provided in the embodiment of the present application; the device includes: an acquisition module 401, a model training module 402, specifically:

[0104] The acquisition module 401 is configured to acquire a sample image library, the sample image library includes multiple sets of sample images, wherein each set of sample images includes a sample image and a tag image corresponding to the sample image, and the sample image includes different objects overlapping image areas, where reference boundary areas between different objects in the sample image are marked in the marked image;

[0105] The model training module 402 is used to use each group of sample images in the sample image library to train the image segmentation model until it is determined that the training of the image segme...

Embodiment 3

[0123] Based on the same technical idea, an embodiment of the present application also provides an electronic device. refer to Figure 6 As shown, it is a schematic structural diagram of an electronic device 600 provided in the embodiment of the present application, including a processor 601 , a memory 602 , and a bus 603 . Among them, the memory 602 is used to store execution instructions, including a memory 6021 and an external memory 6022; the memory 6021 here is also called an internal memory, and is used to temporarily store calculation data in the processor 601 and exchange data with an external memory 6022 such as a hard disk. The processor 601 exchanges data with the external memory 6022 through the memory 6021. When the electronic device 600 is running, the processor 601 communicates with the memory 602 through the bus 603, so that the processor 601 executes the following instructions:

[0124] Obtaining a sample image library, the sample image library includes multi...

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 provides an image segmentation model training method, an image segmentation method and an image segmentation device. The method comprises the steps that firstly, a sample image library is acquired, each group of sample images in the sample image library is used for training an image segmentation model until it is determined that image segmentation model training is completed, and theexecuted training process comprises the steps that pixel values of pixel points of the sample images in the sample image library are adjusted, and a first image corresponding to the sample images isobtained; inputting the first image into an image segmentation model, and outputting a second image after the first image is segmented; calculating a loss value of image segmentation model training according to the second image and the mark image; when the loss value meets the preset condition, it is determined that training of the image segmentation model is completed, and through the method, theimage segmentation accuracy is improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a method for training an image segmentation model, an image segmentation method and a device. Background technique [0002] In the prior art, when segmenting an image containing mutual occlusion by objects, a method of manually segmenting occlusion regions between objects is mainly used to realize the segmentation of images of occlusion object regions. However, when segmenting different images containing different occluded objects, it is necessary to re-divide the occluded areas between different objects, which is inefficient. For example, when performing image segmentation on the lung field area in the chest radiograph image, the existing technology is to design a segmentation method by manually observing the characteristics of the chest radiograph lung field. During image segmentation, it is necessary to manually re-divide the overlapping image areas between...

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): G06T7/11
CPCG06T2207/30061G06T7/11
Inventor 俞宏达胡飞王方
Owner BEIJING PEREDOC TECH CO LTD
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