A tongue image segmentation method based on single target region segmentation

A region segmentation and image segmentation technology, applied in the field of medical image analysis, to reduce the variation of accuracy and improve the calculation speed

Pending Publication Date: 2019-04-05
XIANGTAN UNIV
View PDF8 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, there are currently no deep learning methods dedicated

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
  • A tongue image segmentation method based on single target region segmentation
  • A tongue image segmentation method based on single target region segmentation
  • A tongue image segmentation method based on single target region segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0134] A tongue body image segmentation method based on single target area segmentation, the method comprises the following steps:

[0135] (1) Acquisition of the original image: the original image of the tongue is collected by the image acquisition module;

[0136] (2) Image annotation: through the image annotation module, the Grabcut algorithm improved by superpixels is used to manually annotate each original tongue image collected, and an annotation image corresponding to each original tongue image is obtained;

[0137] (3) Image production: through the image production module, the manually labeled image and the corresponding original tongue image form an image pair; in order to improve the generalization of the model, the original image pair is randomly used as a training set image, and the remaining image pairs are used as test set images;

[0138] (4) Training neural network: train the single-target semantic segmentation neural network through the training set images; ...

Embodiment 2

[0170] Example 1 was repeated, except that α=4 and β=0.7; the number ratio of the training image pair set to the test image pair set was 5:1.

Embodiment 3

[0172] Repeat Example 1, except that α=5, β=1.0; the number ratio of the training image pair set to the test image pair set is 6:1.

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 discloses a tongue image segmentation method based on single-target area segmentation. The method comprises the following steps: step 1) obtaining an original image: collecting the original image of a tongue; Step (2), image annotation: carrying out manual annotation on each collected tongue body original image by adopting a super-pixel improved Grabcut algorithm; (3) image production: forming an image pair by the manually labeled image and a corresponding tongue body original image; Step (4) training the neural network: training the single-target semantic segmentation neural network through the images of the training set; And (5) testing the neural network: segmenting the tongue image by using the trained single-target semantic segmentation neural network, and testing the neural network through the test set image. According to the tongue image segmentation method provided by the invention, a single-target area constraint depth network is adopted to label, segment and learn the existing image to generate the mask image, and then the mask image and the original image are synthesized to form the tongue segmentation image.

Description

technical field [0001] The invention relates to a tongue body image segmentation method based on a deep learning method, in particular to a tongue body image segmentation method based on single target area segmentation, and belongs to the field of medical image analysis. Background technique [0002] As the tongue contains a large amount of information about the body constitution, accurate results can only be diagnosed through rich experience of Chinese medicine experts at this stage. In order to assist the diagnosis of diseases and form a comprehensive computer tongue diagnosis system, it is meaningful to obtain accurate and high-precision tongue images. At present, there have been a lot of research work to segment the tongue in facial images. However, due to interferences such as tongue quality and skin color similarity, tongue coating color change, and tongue deformation, the tongue segmentation effect is not good. [0003] Tongue body image segmentation is the sum of to...

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
IPC IPC(8): G06T7/11G06N7/00G06N3/04
CPCG06N7/00G06T7/11G06T2207/20081G06T2207/30004G06N3/045
Inventor 欧阳建权宋云华陈智能
Owner XIANGTAN UNIV
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