Automatic Segmentation Method of Eye Cup in Fundus Image Based on Improved PDE Image Inpainting
A fundus image, automatic segmentation technology, applied in the field of medical image processing, can solve the problems of the segmentation results remaining in the preliminary stage, the segmentation results are not accurate, and the edge of the optic cup is not clear, so as to reduce manual intervention, ensure accuracy, and ensure The effect of split speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0029] Step 1, read the original image, and normalize the image size to 1440*960 pixels, such as figure 2 .
[0030] Step 2, perform channel selection on the original image, and select the most prominent green channel image U in the target area G Segmentation of the optic cup, such as image 3 .
[0031] Step 3, the image is enhanced through the principle of morphology. This method uses the image top hat and bottom hat transformation to enhance the image:
[0032]
[0033] B hat (U G )=(U G ·SE)-U G
[0034] u CE =(U G +T hat (U G ))-B hat (U G )
[0035] In the formula: symbol Indicates that the image is opened, and the symbol "·" indicates that the image is closed. SE is a structural element, and a circular structural element of 5*5 is taken. T hat (U G ) is the image after top-hat transformation, B hat (U G ) is the image after bottom hat transformation, U CE is the image after contrast enhancement, and the image after image enhancement is as foll...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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