Check patentability & draft patents in minutes with Patsnap Eureka AI!

Automatic identification and analysis method for solving complex flow chart in PDF

A technology for automatic recognition and analysis methods, applied in neural learning methods, character and pattern recognition, instruments, etc.

Pending Publication Date: 2021-09-03
XIAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an automatic identification and analysis method for complex flow charts in PDF, which solves the problem of lack of identification of flow charts in PDF documents 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
  • Automatic identification and analysis method for solving complex flow chart in PDF
  • Automatic identification and analysis method for solving complex flow chart in PDF
  • Automatic identification and analysis method for solving complex flow chart in PDF

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in detail in conjunction with accompanying drawings and specific embodiments.

[0045] like figure 1 As shown in a flowchart of automatic identification and sophisticated analytical method to solve the PDF, the specific steps:

[0046] Step 1, the processing of the initial document

[0047] Specifically Step 1:

[0048] PDF document referred to as the initial A, referred to as a filter condition function L (x), the original document after a desired portion of the remaining filters function referred to as B, B = L (A); then convert the picture function H (x) , filtered document initial condition function, and then convert the picture image through the function referred to as C, C = H (B).

[0049] Step 2, the desired block diagram Faster R-CNN extracting image coordinates based on

[0050] Step 2.1, convolution layer was extracted image features:

[0051] Step 1 obtained through image processing C, and then extracted by a convolution l...

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 an automatic identification and analysis method for solving a complex flow chart in a PDF. The automatic identification and analysis method is specifically implemented according to the following steps: a step 1, processing an initial document; a step 2, extracting coordinates of a required block diagram in the picture based on Faster R-CNN; a step 3, according to the coordinates obtained in the step 2 and the OCR, judging the pointing relation between the entities; and a step 4, constructing a complex network of a pointing relation based on the complex network analysis library NetworkX. Through processing (L(x)) of files and processing (H(x)) of pictures, documents such as plain texts are filtered out, flow chart pages are converted into pictures, and the working time of Faster R-CNN is shortened. The coordinates of the required target block diagram are extracted through the Faster R-CNN, the coordinates of all types of target block diagrams can be extracted at the same time, and the efficiency of recognizing the target coordinates in the image is improved.

Description

Technical field [0001] The present invention belongs to the field of image recognition processing techniques, it involves a complex and automatic recognition of the flowchart in solving analytical method PDF. Background technique [0002] Image recognition technology is an important field of artificial intelligence, which is stereo vision, motion analysis, the basic field data fusion has important application value; a current image and a target plate recognition, face, feature recognition pedestrians more mature . Study of the text is another important field of artificial intelligence, the current study of the text is based on the existing text, research is mainly converted in terms of meaning, word frequency statistics. [0003] However, there are for terms of image recognition of PDF, text parsing and other developing narrow, study only for PDF text key information to split, paragraphs of text information extraction, form weak image analysis information processing, text or high...

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): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241
Inventor 张贝贝刘雅雯郑浩然郭仲穗仵晨伟魏嵬
Owner XIAN UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com