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

Scanning electron microscope image pore identification method based on artificial intelligence

A technology of scanning electron microscopy and artificial intelligence, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of low precision in identifying pores in electron microscopy images, and can not be automated image processing, etc., to achieve the effect of improving accuracy

Active Publication Date: 2018-12-07
JILIN UNIV
View PDF8 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the shortcomings of the traditional image segmentation method to identify the pores of the electron microscope image with low accuracy, the pore identification accuracy is closely related to the parameter setting, and the inability to automate image processing. Human intelligence, significantly improve the accuracy of image segmentation, fully realize automatic processing

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
  • Scanning electron microscope image pore identification method based on artificial intelligence
  • Scanning electron microscope image pore identification method based on artificial intelligence
  • Scanning electron microscope image pore identification method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0025] 1. Image preprocessing. Image preprocessing is to process the image obtained in the experiment into an image that can be used for deep learning, mainly including removing legend and image cutting. Removing the legend is to remove the experimental information marked on the picture in the experiment, and use the image cropping method to cut off the part containing the legend information. Image cutting is to cut an experimental electron microscope image into multiple images according to the pixel size according to the training needs of the deep learning model, so as to reduce the single data processing workload of the deep learning model. Usually, the original data image is cut into 256*256 pixels size. The result is as figure 2 instance.

[0026] 2. Pore marking. Based on the preprocessed SEM image, the positi...

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 present invention discloses a scanning electron microscope image pore identification method based on artificial intelligence, belonging to the field of hydrogeology. The present invention relatesto a rock and soil sample pore parameter obtaining method based on scanning electron microscope images. For the deficiencies that a traditional image segmentation method is low in identification precision of the electron microscope image pore, the pore identification precision and the parameter setting are closely related and the automatic image processing cannot be performed, a deep learning opensource model caffe based on a convolutional neural network is employed to automatically identify the pores in the scanning electron microscope images through a self-learning function of the artificial intelligence by means of the artificial intelligence. The artificial intelligence method provided by the invention can overcome the deficiencies of a current threshold value method, an edge detection method and a neural network method and can greatly improve the identification precision of the pores.

Description

technical field [0001] The patent of the invention belongs to the field of hydrogeology, and relates to a method for obtaining pore parameters of rock and soil samples based on scanning electron microscope images. Background technique [0002] Accurately obtaining rock and soil infiltration parameters in mining areas is the key to quantitative evaluation of water resources and prediction of mine water inflow. Due to inaccurate acquisition of infiltration parameters, the analysis and prediction of mine water inflow does not match the actual situation, which affects the design of mine drainage systems and often causes threats to mines such as flooding. safety incidents. Field pumping (draining) water tests are often used in actual projects to directly obtain seepage parameters, but due to the limitation of the number of exploration holes and test time, the test data is relatively small, and the obtained seepage data are distributed in a point-like manner, and the results usual...

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): G06T7/00G06T7/11
CPCG06T7/0002G06T2207/10061G06T2207/20081G06T7/11
Inventor 于清杨刘伟张超刘晨王城斌
Owner JILIN UNIV
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