Solar film image timestamp information extraction method based on deep learning

A deep learning and information extraction technology, applied in the field of solar observation image processing, can solve the time-consuming and labor-intensive problems of manual identification and extraction, and achieve the effect of rapid positioning and identification

Active Publication Date: 2019-12-03
CHINA THREE GORGES UNIV
View PDF15 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The number of pictures is very large, and manual identification and extraction are time-consuming and laborious

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
  • Solar film image timestamp information extraction method based on deep learning
  • Solar film image timestamp information extraction method based on deep learning
  • Solar film image timestamp information extraction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0067] A general convolutional neural network architecture, including input layer, convolutional layer, pooling layer, fully connected layer and output layer, etc., its structure is as follows figure 1 shown. Through softmax logistic regression, the feature vector output by the output layer is used to classify the input data of the input layer. When the input layer is character image data, the character image can be classified through the classification result of the output layer, and then character recognition can be realized. A convolutional neural network can have multiple convolutional layers, pooling layers, and fully connected layers as needed. figure 1 It is only indicated in its general form.

[0068] The time stamp information in the scanned solar chromosphere film image is extracted by convolutional neural network (CNN), which is mainly divided into three parts, such as figure 2 Shown:

[0069] Step 1, locate and crop the time stamp information area of ​​the imag...

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 discloses a solar film image timestamp information extraction method based on deep learning, and the method comprises the steps: step 1, positioning and cutting a timestamp information rarea in a solar color ball film image; wherein the timestamp information is year, month, day, hour and minute information used for representing shooting time in the sun color ball film image; step 2,segmenting single characters: further segmenting the characters in the timestamp information area to obtain single characters; and step 3, character recognition: firstly, training a network by adopting a large number of samples, then recognizing the single character obtained by segmentation in the step 2 by using the trained network, and integrating and storing recognition results of the single character. A digital timestamp in a solar observation image film is automatically recognized by a machine, and recognized time information is output. Therefore, the workload of manual identification and time information writing is reduced, the digitization process of the batch of film data can be accelerated, and the precious historical data can be more conveniently used for solar physics research.

Description

technical field [0001] The invention relates to the technical field of solar observation image processing, in particular to a method for extracting timestamp information of solar film images based on deep learning. Background technique [0002] The sun's chromosphere is a layer of atmosphere above the photosphere. As the transition zone from the photosphere to the corona, the magnetic field is not stable, and violent flares often occur. Radiation from solar flares in the chromosphere often appears as elongated ribbons on both sides of the magnetic pole inversion line (PIL), which is considered evidence of a typical pattern of magnetic reconnection. In order to study the phenomenon of flare eruption, relevant personnel need to take pictures and records of the solar chromosphere for a long time. Due to the huge amount of historical data, the time information of a large number of chromospheric images is still presented in the data in the form of images, and has not formed digi...

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): G06K9/32G06K9/34G06K9/62
CPCG06V20/62G06V10/267G06V30/10G06F18/241
Inventor 曾曙光左肖雄郑胜张佳锋曾祥云
Owner CHINA THREE GORGES UNIV
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