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

Microscopic image data enhancement method and device

A microscopic image and enhancement device technology, which is applied in the field of measuring microscopes, can solve a large number of manual labeling problems, and achieve the effect of meeting the needs of training samples, reducing the number, time and labor costs

Active Publication Date: 2019-07-12
UNIV OF SCI & TECH BEIJING
View PDF10 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a microscopic image data enhancement method and device to solve the problem that a large number of manual annotations are required in the microscopic image analysis task existing in the prior art

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
  • Microscopic image data enhancement method and device
  • Microscopic image data enhancement method and device
  • Microscopic image data enhancement method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as figure 1 As shown, the microscopic image data enhancement method provided by the embodiment of the present invention includes:

[0051] S101, generating a virtual image of a real microscopic image;

[0052] S102. Transfer the style of the real microscopic image to the virtual image by using a style transfer method;

[0053] S103, according to the calculation and simulation characteristics of the virtual image, obtain the corresponding semantic annotations from each semantic region of the virtual image, combine the virtual image with a real microscopic image style and the corresponding semantic annotations to form annotated image data, to train image analysis Model.

[0054] The microscopic image data enhancement method described in the embodiment of the present invention generates a virtual image of a real microscopic image; transfers the style of the real microscopic image to the virtual image through a style transfer method; according to the calculation and ...

Embodiment 2

[0106] The present invention also provides a specific implementation of a microscopic image data enhancement device. Since the microscopic image data enhancement device provided by the present invention corresponds to the specific implementation of the aforementioned microscopic image data enhancement method, the microscopic image data enhancement device The purpose of the present invention can be achieved by executing the process steps in the specific implementation of the above method, so the explanations in the specific implementation of the microscopic image data enhancement method above are also applicable to the specific implementation of the microscopic image data enhancement device provided by the present invention. Embodiments will not be repeated in the following specific embodiments of the present invention.

[0107] Such as Figure 8 As shown, the embodiment of the present invention also provides a microscopic image data enhancement device, including:

[0108] Gen...

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 provides a microscopic image data enhancement method and device, which can automatically label images. The method comprises the following steps: generating a virtual image of a real microscopic image; migrating the style of the real microscopic image to the virtual image through a style migration method; obtaining corresponding semantic annotations from each semantic area of the virtual image according to the computational simulation characteristics of the virtual image, and combining the virtual image with a real microscopic image style with the corresponding semantic annotations to form annotated image data so as to train an image analysis model. The invention relates to the technical field of measuring microscopes.

Description

technical field [0001] The invention relates to the technical field of measuring microscopes, in particular to a method and device for enhancing microscopic image data. Background technique [0002] In the research of materials science, medicine, electronic devices, micromechanics and other fields, researchers usually use microscopes to take microscopic images, then observe microstructures or microstructures, and use image analysis methods to extract regions of interest or targets in the images The characteristics of the final material / organ tissue analysis or device quality assessment, etc. At present, in image classification, image object detection, image segmentation and other tasks, image analysis methods based on convolutional neural networks have achieved breakthrough results in analysis accuracy and efficiency. However, in the actual operation process, this method requires a large amount of manually labeled data for the algorithm training model, resulting in low gene...

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): G06K9/62G06N3/04G06T11/00
CPCG06T11/001G06N3/045G06F18/2411G06F18/214
Inventor 班晓娟魏晓燕马博渊黄海友王浩薛维华
Owner UNIV OF SCI & TECH BEIJING
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