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

Handwritten text line character segmentation method and identification method

A text line and character technology, applied in the field of handwritten text line character recognition and handwritten text line character segmentation, can solve the problems of indistinct character boundaries, time-consuming, and unsatisfactory segmentation effects, and achieve convenient character recognition processing. Effect

Inactive Publication Date: 2011-08-17
SHANGHAI HEHE INFORMATION TECH DEV
View PDF0 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the former has higher segmentation accuracy, but it takes a lot of time; the latter is simpler to implement, but the segmentation effect is not ideal.
Moreover, in the above methods, it is impossible to better segment the boundaries between characters, such as overlapping and sticking.

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
  • Handwritten text line character segmentation method and identification method
  • Handwritten text line character segmentation method and identification method
  • Handwritten text line character segmentation method and identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] The present invention provides a fast unconstrained handwritten text line segmentation method, which can accurately segment the text line. Three common situations in naturally written Chinese text lines: naturally separated characters, overlapping characters, and glued characters are processed separately. For naturally separated characters, use the histogram projection method to segment them; for overlapping characters, use the method of setting isolation points in the overlapping area to segment them; for glued characters, first detect the glued points, and then Split the characters at the glue point, and finally divide them as overlapping characters. The method of the present invention can ensure high segmentation accuracy while realizing rapid segmentation of text lines.

[0064] The present invention proposes a character segmentation technical method for three common situations in non-unconstrained natural writing Chinese text lines: naturally separated characters, ov...

Embodiment 2

[0101] This embodiment discloses a method for recognizing characters in a handwritten text line. The method includes the following steps:

[0102] Step S10: input a text line;

[0103] Step S20: Divide the naturally separated characters;

[0104] Step S30: Estimate the width of each character based on the result obtained in step S20, and determine whether the character width is greater than the preset threshold T; if yes, go to step S40; otherwise, go to step S70;

[0105] Step S40: Perform overlapping character segmentation;

[0106] Step S50: Estimate the width of each character based on the result obtained in step S40, and determine whether the character width is greater than the preset threshold T; if yes, go to step S60; otherwise, go to step S70;

[0107] Step S60: Perform segmentation of glued characters;

[0108] Step S70: output the segmentation result;

[0109] Step S80: Recognize the characters obtained from the output segmentation results respectively, and output the recognitio...

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 a handwritten text line character segmentation method and an identification method, which can accurately segment text lines. Three common conditions of naturally isolated characters, superposed characters and merged characters in a naturally written Chinese character text are respectively processed. The naturally isolated characters are segmented through a histogram projection method; the superposed characters are segmented by setting isolating points in a superposed region; and the merged characters are segmented through steps of firstly detecting out merged points in the merged characters, then, separating the characters at the merged points and finally segmenting the characters as the superposed characters. The methods provided by the invention can ensure higher segmentation accuracy while implementing rapid segmentation of the text lines.

Description

Technical field [0001] The invention belongs to the technical field of image processing and handwritten character recognition, and relates to a character segmentation method, in particular to a character segmentation method for handwritten text lines; meanwhile, the present invention also relates to a method for recognizing handwritten text line characters. Background technique [0002] Human-computer natural communication is an important development direction of human-computer interaction in the future, and text is one of the means of natural communication between humans and computers. According to the description of human natural language, the user’s handwritten text is obtained through certain methods and technical means (such as using touch screens, scanners or cameras), and then certain technical methods are used to analyze and process the handwritten text images to realize the computer to the text The automatic recognition, which is what we call text recognition. [0003] At...

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): G06K9/20G06K9/34
Inventor 镇立新
Owner SHANGHAI HEHE INFORMATION TECH DEV
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