Formula identification method and device

A formula recognition and behavior technology, applied in the field of machine learning, can solve the problems of complex recognition steps, long recognition time, and low accuracy rate, and achieve the effect of reducing recognition time, simplifying recognition steps, and increasing recognition accuracy

Pending Publication Date: 2020-04-21
HUAZHONG NORMAL UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Each step in the process of formula recognition is independent, resulting in that the recognition process does not consider the timing of the formula, the recognition steps are complicated, the recognition time is long, and the accuracy is low

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
  • Formula identification method and device
  • Formula identification method and device
  • Formula identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] see figure 2 A flow chart of a formula recognition method is shown, the method includes the following steps:

[0037] Step S202, acquiring data to be processed.

[0038] Data to be processed refers to formula data that needs to be identified. Generally speaking, the formula can be a mathematical formula, a physical formula, a chemical formula, etc. using a mathematical symbol table. The data to be processed can be directly input by the user, or can be obtained by scanning an image with a formula.

[0039] Step S204, extracting handwriting features of the data to be processed; the handwriting features include stroke position features and geometric features.

[0040] Handwriting features are used to describe the characteristics of the strokes that make up the formula. The data to be processed includes the position and geometric shape of each point in the formula. By taking part of the data representing the coordinates as a whole, the position characteristics of the s...

Embodiment 2

[0047] The embodiment of the present invention also provides another formula recognition method; this method is implemented on the basis of the method in the above embodiment; this method focuses on the specific implementation of extracting the handwriting features of the data to be processed.

[0048] Such as image 3 A flow chart of another formula identification method is shown, the method includes the following steps:

[0049] Step S302, acquiring data to be processed.

[0050] Here, the writer writes the formula into the touch screen, and the method provided in this embodiment identifies the data to be processed provided by the touch screen as an example, see Figure 4 A schematic diagram of a formula recognition method is shown, such as Figure 4 As shown, the writer writes formulas through a device with a touch screen (such as an electronic whiteboard or a tablet computer), and the touch screen will perform feature extraction after preprocessing the collected data to ...

Embodiment 3

[0109] Corresponding to the above method embodiment, the embodiment of the present invention provides a formula recognition device, such as Figure 7 A structural schematic diagram of a formula recognition device shown, the device includes:

[0110] A data acquisition module 71, configured to acquire data to be processed;

[0111] Feature extraction module 72, is used for extracting the handwriting feature of data to be processed; Handwriting feature comprises position feature and geometric feature of stroke;

[0112] The behavior chain construction module 73 is used to generate the user behavior chain corresponding to the data to be processed according to the input sequence and handwriting characteristics of the strokes in the data to be processed; the user behavior chain is used to indicate the timing relationship between symbols in the data to be processed;

[0113] The recognition model module 74 is configured to input the user behavior chain into the preset formula 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 provides a formula identification method and device. The method comprises the steps of obtaining to-be-processed data; extracting handwriting features of the to-be-processed data; generating a user behavior chain corresponding to the to-be-processed data according to the input sequence of strokes in the to-be-processed data and the handwriting features, wherein the user behavior chain is used for indicating a time sequence relationship between symbols in the to-be-processed data; and inputting the user behavior chain into a preset formula identification model, and outputting a formula identification result of the to-be-processed data. The method comprises the steps of generating a user behavior chain capable of indicating a time sequence relationship between symbols in to-be-processed data according to an input sequence and handwriting characteristics of strokes in the to-be-processed data; inputting the user behavior case into a preset formula recognition model, outputting a formula recognition result by the formula recognition model, indicating a time sequence relationship through a user behavior chain, and considering the time sequence of the formula in the recognition process, so as to simplify the recognition steps, shorten the recognition time and improve the recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a formula recognition method and device. Background technique [0002] Technical problem: In related technologies, formulas can be identified by combining symbol recognition and structural analysis. This method requires symbol recognition for each character after the formula data is segmented, and then structural analysis. Each step in the process of formula recognition is independent, resulting in that the recognition process does not consider the timing of the formula, the recognition steps are complicated, the recognition time is long, and the accuracy rate is low. Contents of the invention [0003] In view of this, the object of the present invention is to provide a formula recognition method and device, which considers the timing of formulas during the recognition process, so as to simplify the recognition steps, reduce the recognition time, and increase the recog...

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): G06K9/00G06K9/62G06N20/00
CPCG06N20/00G06V30/347G06V30/36G06F18/241
Inventor 张浩黄涛刘三女牙杨宗凯杨华利夏雨
Owner HUAZHONG NORMAL 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