Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fuzzy boundary image automatic segmentation method based on active contour and deep learning

A technology of deep learning and blurred boundaries, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as difficult to deal with complex images, and achieve the effect of improving accuracy

Active Publication Date: 2020-01-14
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the active contour model needs to initialize the contour, which is difficult to deal with complex images

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
  • Fuzzy boundary image automatic segmentation method based on active contour and deep learning
  • Fuzzy boundary image automatic segmentation method based on active contour and deep learning
  • Fuzzy boundary image automatic segmentation method based on active contour and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] An automatic segmentation method for fuzzy boundary images based on active contours and deep learning, such as Figure 8 shown, including the following steps:

[0083] S1. For a fuzzy boundary image, such as figure 1 For the ultrasound image of the thyroid gland shown, use the trained U-Net convolutional neural network model to segment the thyroid region to obtain the U-Net segmentation result image;

[0084] S2. Use the active contour model to fine-tune the segmentation results of the model to obtain more accurate normal boundary and fuzzy boundary segmentation results, such as Figure 8 shown, including the following steps:

[0085] S2.1. Use image 3 The boundary of the thyroid region in initializes the active contour model, and constructs the initial level set φ I (x, y); set the parameters of the active contour model as μ=1, v=0, λ 1 =1,λ 2 =1,λ 3 =1,Δt=0.1,R=8,c d =8, ε=1; the definition of the initial level set is as follows:

[0086]

[0087] Among t...

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 fuzzy boundary image automatic segmentation method based on an active contour and deep learning. The method comprises the following steps: firstly, segmenting a fuzzy boundary image by using a deep convolutional neural network model to obtain an initial segmentation result; then, using an image internal region contour segmented by the deep convolutional neural network model as an initialization contour and contour constraint of an active contour model; the active contour model driving the contour to move towards the edge of the target through the image characteristicsof the area around each contour point, and obtaining an accurate segmentation line between the target area and other background areas. According to the method, the active contour model is introducedon the basis of the deep convolutional neural network model to further refine the segmentation result of the blurred boundary image, the capability of segmenting the blurred boundary in the image is achieved, and the segmentation accuracy of the blurred boundary image is further improved.

Description

technical field [0001] The invention belongs to the technical field of fuzzy boundary image processing, in particular to an automatic segmentation method of fuzzy boundary images based on active contours and deep learning. Background technique [0002] The difficulty of fuzzy image segmentation is that it is difficult to accurately locate complex boundaries and correctly segment tiny isolated objects. Complex boundaries include blurred boundaries, vanishing boundaries, complex interaction of boundaries, changeable shapes, etc. Ultrasound image is a common blurred image. Its low contrast and noisy features often make the edge of the target blur or even disappear. The actual boundary of the target is easily affected by artifacts, and even partially covered by a large number of artifacts. Accurate segmentation of images with blurred boundaries has become a current challenge. [0003] In recent years, deep convolutional neural network models have achieved remarkable results in...

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): G06T7/11G06T7/12G06T7/00
CPCG06T7/11G06T7/12G06T7/0012G06T2207/20081G06T2207/20084G06T2207/30004G06T2207/10132G06T7/149G06T2207/20116G06T7/62G06T2207/20161
Inventor 陈俊颖游海军
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com