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

Structure Analysis and Recognition Method of Handwritten Mathematical Formulas in Natural Scene Images

A technology of natural scene images and mathematical formulas, applied in the field of structural analysis and recognition of handwritten mathematical formulas, to achieve accurate recognition and solve representation problems

Active Publication Date: 2018-08-03
BEIJING YUNJIANG TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The method for structural analysis and recognition of handwritten mathematical formulas in natural scene images provided by the present invention can effectively solve the problem of representation of elementary mathematical formulas in OCR recognition

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
  • Structure Analysis and Recognition Method of Handwritten Mathematical Formulas in Natural Scene Images
  • Structure Analysis and Recognition Method of Handwritten Mathematical Formulas in Natural Scene Images
  • Structure Analysis and Recognition Method of Handwritten Mathematical Formulas in Natural Scene Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The method for analyzing and recognizing the structure of handwritten mathematical formulas in natural scenes provided by the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0056] like figure 1 As shown, the handwritten mathematical formula structure analysis and recognition method in the natural scene provided by the embodiment of the present invention includes the following steps:

[0057] Step S1, converting the grayscale matrix of the natural scene image into a local contrast matrix, and using the otsu method to perform binary division on the obtained local contrast matrix to obtain a binary matrix;

[0058] In this embodiment, the formula for calculating the local contrast Con(i,j) of a point whose coordinates are (i,j) in the local contrast matrix is:

[0059] Con(i,j)=αC(i,j)+(1-α)(I max (i,j)-I min (i,j))

[0060] in,

[0061] I max (i, j) and I min (i, j) are the maximum gray value and ...

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

A method for analyzing and recognizing the structure of handwritten mathematical formulas in a natural scene image, comprising: S1, converting the grayscale matrix of the natural scene image into a local contrast matrix, and using the otsu method to perform binary division on the obtained local contrast matrix to obtain binary values Matrix; S2, analyzing the connected domains of the binary matrix in step S1, eliminating the non-character connected domains to obtain the character connected domains; S3, using the correlation coefficient method to detect the special structural elements of the formula in the character connected domains in S2, and all The detected special structural elements are marked separately; S4, use the horizontal projection method to divide the binary matrix in S1 into rows; S5: use the convolutional neural network to identify the connected domain of each character; S6, define the output sequence, and set The recognition results are output in the latex typesetting format in the corresponding order. This method effectively solves the problem of expressing elementary mathematical formulas in OCR recognition.

Description

technical field [0001] The invention relates to image processing and pattern recognition technology, in particular to a method for analyzing and recognizing the structure of handwritten mathematical formulas in natural scene images. Background technique [0002] OCR (Optical Character Recognition, Optical Character Recognition) technology has a wide range of applications, and the OCR recognition technology for Chinese and English is relatively mature, but for the complex structure of mathematical formulas, the current OCR technology is not very good. Support, the present invention focuses on solving this problem with strong application requirements. Contents of the invention [0003] The method for analyzing and recognizing the structure of handwritten mathematical formulas in natural scene images can effectively solve the problem of expressing elementary mathematical formulas in OCR recognition. [0004] The method for analyzing and recognizing the structure of handwritt...

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): G06K9/32G06K9/62G06N3/02
CPCG06N3/02G06V20/63G06V10/751G06V30/10
Inventor 陈李江刘宁刘辉
Owner BEIJING YUNJIANG TECH CO LTD
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