A method, device, device and storage medium for chart recognition

A recognition method and chart technology, applied in the field of image recognition, can solve the problems of low efficiency and low accuracy of chart recognition, and achieve the effect of rich data types, universality and robustness guarantee

Active Publication Date: 2022-07-12
珠海盈米基金销售有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a chart recognition method, device, equipment and storage medium, which can solve the technical problems of low efficiency and low accuracy in identifying charts from text files 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
  • A method, device, device and storage medium for chart recognition
  • A method, device, device and storage medium for chart recognition
  • A method, device, device and storage medium for chart recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1This is a flowchart of a method for identifying a chart provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of recognizing graph data in text files of various formats. The graph recognizing method proposed in this embodiment can be executed by a graph recognizing device, and the graph recognizing device can be performed by software and / or hardware. Implementation can be configured in computer equipment, for example, computing equipment such as servers, personal computers, mobile terminals, etc., and the method specifically includes the following steps:

[0050] S110. Acquire a text file containing chart data.

[0051] In this embodiment, the chart data includes image data composed of tables, pure table data, etc., wherein the image data composed of tables may include a line graph class generated according to the table data, a bar graph class (eg Column charts, histograms, stacked column charts, etc.), column and bar cha...

Embodiment 2

[0104] figure 2 This is a structural block diagram of a chart recognition device provided in Embodiment 2 of the present invention, and the device can be implemented by software and / or hardware. The device includes: a data acquisition module 201, a format conversion module 202 and a chart identification module 203, wherein,

[0105] A data acquisition module 201, for acquiring a text file containing chart data;

[0106] a format conversion module 202, for converting the text file into a picture in a preset format;

[0107] The chart identification module 203 is used for inputting the picture into a chart positioning detector, and outputting a positioning result of the chart data in the picture; wherein, the chart positioning detector includes a sample chart by a preset neural network A sample dataset of data obtained from training.

[0108] In one embodiment of the present invention, the preset neural network is Yolov5s network or Yolov5l network or Yolov5m network or Yolo...

Embodiment 3

[0138] image 3 A schematic structural diagram of a computer device provided in Embodiment 3 of the present invention, such as image 3 As shown, the computer device includes a processor 300, a memory 310, an input device 320 and an output device 330; the number of processors 300 in the computer device may be one or more, image 3 Take a processor 300 as an example in the above; the processor 300, the memory 310, the input device 320 and the output device 330 in the computer equipment can be connected by a bus or other means, image 3 Take the connection through the bus as an example.

[0139] As a computer-readable storage medium, the memory 310 can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the diagram recognition method in the embodiment of the present invention (for example, data acquisition in the diagram recognition device). module 201, format conversion module 202 and chart recog...

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 chart recognition method, device, equipment and storage medium. The method includes: acquiring a text file containing chart data; converting the text file into a picture in a preset format; inputting the picture into a chart positioning detector, and outputting The positioning result of the chart data in the picture; wherein, the chart positioning detector is obtained by training a preset neural network through a sample data set containing sample chart data. The text file containing chart data in the present invention can be a text file of any format and type, and converting the text file into a picture avoids the need to use a standard protocol to parse the text to locate the chart position in the prior art. If the picture is directly input into the pre-trained chart positioning detector, the positioning result of the chart data in the picture can be directly output, which can solve the problem that the existing technology is inefficient in identifying charts from text files and the accuracy of identifying charts is low. question.

Description

technical field [0001] Embodiments of the present invention relate to image recognition technology, and in particular, to a method, device, device, and storage medium for chart recognition. Background technique [0002] In the field of data analysis, it is most intuitive to obtain effective information from chart data. The morphological analysis of chart data is often one of the important analysis methods in finance, scientific research and other industries. The effectiveness of its data analysis has also been obtained in all walks of life. Extensive validation. [0003] Since the chart data is generally attached to the text file, it is often necessary to extract the charts in each text file separately when using the chart data for analysis. However, the traditional chart extraction method, one is based on CPU computing equipment for processing, which needs to parse the text file in advance, which leads to high time cost, slow extraction speed and long time. The format of ...

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 Patents(China)
IPC IPC(8): G06V30/413G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F18/241
Inventor 吴珂皓薛逢源李博岩
Owner 珠海盈米基金销售有限公司
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