Intelligent identification method and system for hand-written table

An intelligent recognition and table technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of increasing table format, difficulty, table format fixed, etc., to achieve strong robustness, fast and accurate recognition, strong The effect of practicality

Active Publication Date: 2015-04-01
UNIV OF SCI & TECH OF CHINA
View PDF1 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Restricted form recognition can greatly improve the accuracy and speed of computer recognition of forms, but the recognized form format is fixed, usually only a few, and it is d

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
  • Intelligent identification method and system for hand-written table
  • Intelligent identification method and system for hand-written table
  • Intelligent identification method and system for hand-written table

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] figure 1 It is a flow chart of an intelligent recognition method for a handwritten form provided by Embodiment 1 of the present invention. Such as figure 1 As shown, the method mainly includes the following steps:

[0021] Step 11. After preprocessing the photographed handwritten form pictures, sequentially perform difference processing and Hough transform to obtain angle-corrected handwritten form pictures.

[0022] In actual work, due to factors such as shooting angle and jitter in the process of image collection, the image will be distorted to a certain extent.

[0023] Exemplary, figure 2 This step can be used to correct the handwritten form pictures taken; specifically:

[0024] First, after graying the picture of the handwritten form, use the maximum inter-class difference method to obtain the global threshold, and perform binarization to obtain the picture F1;

[0025] Next, perform a vertical difference on the picture F1 to obtain a picture F2 after the di...

Embodiment 2

[0057] Image 6 It is a schematic diagram of an intelligent recognition system for a handwritten form provided by Embodiment 1 of the present invention. Such as Image 6 As shown, the system mainly includes:

[0058] Correction module 61, after being used for preprocessing the photographed handwritten form picture, sequentially carry out differential processing and Hough transform, obtain the handwritten form picture after angle correction;

[0059] A rectangular area extraction module 62, configured to segment the angle-corrected handwritten form picture to obtain several rectangular areas including handwritten parts;

[0060] The identification module 63 is configured to analyze and identify the content in the several rectangular areas based on features or classifiers.

[0061] Further, the angle correction module 61 may include:

[0062] The binarization module 611 is used for graying the handwritten form picture, using the maximum inter-class difference method to obtai...

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 intelligent identification method and system for a hand-written table. The method comprises the following steps: after carrying out preprocessing on a hand-written table image obtained by shooting, carrying out differential treatment and hough transformation in sequence to obtain the hand-written table image obtained after angle correction; carrying out segmentation on the hand-written table image obtained after angle correction to obtain a plurality of rectangular regions comprising hand-written portions; and carrying out analysis and identification on the contents in the plurality of rectangular regions based on characteristics or a classifier. Through the method and system disclosed in the invention, the hand-written table can be identified quickly and accurately.

Description

technical field [0001] The invention relates to the technical field of intelligent image analysis, in particular to an intelligent recognition method and system for a handwritten form. Background technique [0002] Tables are commonly used data carriers in documents. At present, they are widely used in various occasions such as business and social surveys. However, the statistical analysis of table results is often a task with a huge workload. In the statistics of traditional evaluation tables, people often need to do it manually, which greatly wastes manpower and material resources. [0003] Currently existing form recognition systems can be divided into two categories: [0004] Unrestricted table recognition: There is no prior structural information of the table before recognition, mainly by analyzing the table structure of the picture, and then extracting and recognizing characters after obtaining the structure of the table. The algorithm is complex, and the recognition...

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): G06K9/00G06K9/20G06K9/66
CPCG06V30/413G06V30/414G06V10/243G06F18/24
Inventor 董兰芳谢永祥
Owner UNIV OF SCI & TECH OF CHINA
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