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

Full-automatic segmentation system and method for microscopic image of neural crest cells

A microscopic image and image segmentation technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of large number of cells, large difference between cell edge shape and real, image over-segmentation and straight edge, etc., to achieve Accurate and clear edges, enhance the accuracy and intelligence of segmentation, and alleviate the effect of over-segmentation

Active Publication Date: 2017-01-04
SICHUAN MUNIULIUMA INTELLIGENT TECH CO LTD
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the technical problems that the number of cells in the image segmentation method in the prior art is more than the real situation and the shape of the cell edge is greatly different from the real one. The present invention discloses a fully automatic neural crest cell microscopic image segmentation system and method
The above method solves the problem of over-segmentation and straight edge of the prior art image

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Specific embodiments of the present invention will be described in detail below. When the normalized cut image segmentation method is used to automatically segment microscopic images, the artificially annotated binary background truth map is used for parameter optimization.

[0020] The artificially labeled binary background truth map is used for parameter optimization, mainly by combining the segmentation criterion and similarity segmentation criterion in the traditional normalized cut image segmentation method, and optimizing the traditional normalized cut image segmentation method by maximizing this segmentation criterion parameters in .

[0021] Combining the segmentation criterion and similarity segmentation criterion in the traditional normalized cut image segmentation method, the similarity segmentation criterion specifically refers to the pixel similarity between the segmentation result in the segmentation process and the manually labeled binary background truth...

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 microscopic image segmentation technology, and discloses a full-automatic segmentation system and method for a microscopic image of neural crest cells. The method specifically comprises the following steps: 1, building a microscopic image with a mark, i.e., carrying out the marking through a manual method, and obtaining binary ground truth images; 2, segmenting the microscopic image through employing a conventional Normalized Cut segmentation method; 3, carrying out the adjustment and optimization of the parameters in the conventional Normalized Cut segmentation method at step 2 through combining with the images at step 1, and achieving the Supervised Normalized Cut segmentation method. The method employs a supervised method for image segmentation, and improves the accuracy of image segmentation.

Description

technical field [0001] The invention relates to microscopic image segmentation technology, and the invention discloses a fully automatic neural crest cell microscopic image segmentation system and method. Background technique [0002] In the prior art, the watershed algorithm is generally used to segment the microscopic images of neural crest cells. The method generally consists of three steps: [0003] (1) Acquisition of original microscopic images of neural crest cells. Two images can be obtained for each sampling, one for the cytoplasm and the other for the nucleus. [0004] (2) Locate each neural crest cell using the correspondence between the cytoplasmic map and the nuclear map. In the positioning process, the nucleus that exists alone is a dying cell with atrophied cytoplasm, which is not considered; the cell with both the nucleus and the cytoplasm is a healthy cell, and it is located; the cell with no nucleus and only the cytoplasm is an unhealthy cell ,Not be con...

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
CPCG06T2207/10061G06T2207/20081G06T2207/30024
Inventor 李晨蒋涛黄欣宇
Owner SICHUAN MUNIULIUMA INTELLIGENT TECH CO LTD
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