A method for describing sunspot group in full-sun image

A technology in sunspots and images, which is applied in still image data retrieval, still image data indexing, still image data clustering/classification, etc. It can solve the problems that the sunspot group description is not involved, and achieve the effect of improving the description quality

Active Publication Date: 2020-02-28
KUNMING UNIV OF SCI & TECH
View PDF10 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, image description technology is generally used in some daily image scenes, but the research on sunspot group description has not covered

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
  • A method for describing sunspot group in full-sun image
  • A method for describing sunspot group in full-sun image
  • A method for describing sunspot group in full-sun image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] Embodiment 1: as Figure 1-4 As shown, a method for describing the sunspot group in the full sun image, the steps are as follows:

[0022] Step 1: Sunspot group image dataset: convert the full sunspot group image into an image format recognizable by the VGG-16 network; use the image annotation tool to make the sunspot group image dataset according to the converted image according to the Zurich classification;

[0023] Specifically, convert the full sunspot group image in HMI format into JPG / PNG format, and then use the labelimg tool to create a sunspot group image dataset according to the Zurich classification method.

[0024] Step 2: Sunspot group description text dataset: manually add its corresponding feature description to each sunspot group image in the classified sunspot group image dataset obtained through step 1; the feature description is based on each sunspot group image in each sunspot group image A group is described as an object, and the specific descripti...

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 a method for describing a sunspot group in a full-sun image, and belongs to the field of computer vision and natural language processing. The method comprises the following steps of: making a sunspot group image and a data set for describing a text, sending an original image into an improved VGG-16 network to generate a feature map; sending the output feature map to a positioning layer, generating candidate regions through improved Inception-RPN, processing the candidate regions into region features with fixed sizes, processing the region features into one-dimensionalvectors capable of being processed by LSTM after passing through an identification network, and finally generating description statements; compared with a traditional method, the method has the advantages that more accurate candidate regions can be obtained, so that the description quality of the whole network is improved.

Description

technical field [0001] The invention relates to a method for describing sunspot groups in a full sun image, belonging to the fields of computer vision and natural language processing. Background technique [0002] The sunspot groups on the surface of the sun are rich in forms, and different forms of sunspot groups are closely related to solar activities. Therefore, accurate detection and description of sunspot groups in full-helioscopic images can provide a basis for monitoring and predicting solar activities. [0003] Image description is to automatically generate a descriptive text based on the given picture, which is a description of the nature and relationship between each component in the image. The existing methods are mainly divided into the following three categories: template-based methods, which are simple and intuitive, but due to the limitation of fixed sentence templates, the generated description sentence structure is often relatively single and rigid, and the ...

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): G06F16/51G06F16/583G06F16/55G06K9/32G06K9/62G06N3/04
CPCG06F16/51G06F16/583G06F16/55G06V10/25G06N3/045G06F18/241
Inventor 杨云飞刘海燕朱健李小洁
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap