Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic identification and analysis method for finite tables

A technology of automatic recognition and analysis method, applied in the field of image recognition, can solve the problem of accuracy, applicability cannot be guaranteed, and achieve the effect of considerable accuracy

Pending Publication Date: 2021-05-28
XIAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although the current research has analyzed pure text or highly unified weak images such as PDF text table information processing, the accuracy and applicability are still not guaranteed.

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 finite tables
  • Automatic identification and analysis method for finite tables
  • Automatic identification and analysis method for finite tables

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0044] Such as Figure 7 As shown, a method for automatic recognition and analysis of limited tables is implemented according to the following steps:

[0045] Step 1. Filter the form;

[0046] Step 2, use the opencv library to locate the selected table.

[0047] Such as figure 1 As shown, step 1 is specifically implemented according to the following steps:

[0048] Step 1.1, input the original document as A, and convert the pdf file A into a picture set B=F(A) through the picture conversion function F(x);

[0049] Step 1.2, process the picture by grayscale and adaptive threshold and binarization;

[0050] Step 1.3, filter the processed pictures by erosion and expansion;

[0051] Step 1.4, use the opencv library for secondary screening.

[0052] Step 1.2 is specifically:

[0053] First grayscale the picture set B, find the threshold, t...

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 finite tables. The method is specifically implemented according to the following steps: step 1, screening tables; step 2, positioning the screened table by using an opencv library; converting all pdf files into a picture set, carrying out screening and positioning, dividing the screening process into two parts, wherein the first part is used for screening more than one row of large tables, and the second part is used for screening the special situation that only one row exists or only one row exists in the left half part; and preventing the table with only one line from being deleted in the first part due to too small area and the table with only one line in the left half part from losing partial information in the first part due to special conditions, and finally positioning and outputting all screened tables. Through two screening processes, the invention has considerable correctness and practicability.

Description

technical field [0001] The invention belongs to the technical field of image recognition and relates to a method for automatic recognition and analysis of limited tables. Background technique [0002] Image recognition technology is an important field of artificial intelligence. It is the basis of practical technologies such as stereo vision, motion analysis, and data fusion. It has important application value in many fields. Image target recognition is relatively mature for feature recognition such as pedestrians, license plates, and faces. The research on the text is based on the existing texts, including word meaning conversion, word frequency statistics and so on. [0003] Although the current research has analyzed pure text or highly unified weak images such as PDF text table information processing, the accuracy and applicability are still not guaranteed. People widely use various tables in communication, scientific research and data analysis activities. For tables o...

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): G06K9/00G06K9/62
CPCG06V30/413G06F18/2415
Inventor 张贝贝郭仲穗郑浩然李虹岩邬凛魏嵬
Owner XIAN UNIV OF TECH