Fundus image blood vessel segmentation method based on full convolutional neural network multi-scale features
A convolutional neural network and multi-scale feature technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve the problems that neural networks cannot segment blood vessel images well, the segmentation effect is poor, and there are many additional conditions , to achieve the effect of avoiding the image processing process
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0014] The present invention will be further described below in conjunction with the schematic diagram.
[0015] Reference figure 1 with figure 2 , A method for blood vessel segmentation in fundus images based on multi-scale features of a fully convolutional neural network, including the following steps:
[0016] 1) Image preprocessing
[0017] The quality of the image directly affects the accuracy of the effect. The purpose of image preprocessing is to eliminate irrelevant information in the image, simplify the data to the greatest extent, and overcome image interference. First, assign different weights to the values of the R, G, and B channels of each color retinal image according to the formula Gray=R*0.299+G*0.587+B*0.114, and convert the image into a single-channel grayscale image. Then perform normalization processing to improve the contrast and clarity of the blood vessels in the picture. Finally, Gamma correction is performed to enhance the contrast of the image. After...
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