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

On-line identification method and recognition system for 'ding' of handwriting Tibet character

A recognition method and technology of a recognition system, applied in the field of online handwritten character recognition, can solve problems such as online handwritten recognition that have not been seen

Active Publication Date: 2009-08-19
NORTHWEST UNIVERSITY FOR NATIONALITIES
View PDF0 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, there are no other related literature reports on online handwriting 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
  • On-line identification method and recognition system for 'ding' of handwriting Tibet character
  • On-line identification method and recognition system for 'ding' of handwriting Tibet character
  • On-line identification method and recognition system for 'ding' of handwriting Tibet character

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0100] The Tibetan character recognition scheme is implemented through the following steps, and its system composition is as follows figure 1 As shown, there are training phase and recognition phase respectively. The last is the syllable association to the recognized letter.

[0101] Steps in the training phase:

[0102] Step 1. Sample Collection

[0103] There are 562 Tibetan characters in modern Tibetan. Using the handwritten version and our sampling software, nearly 300 Tibetan students wrote samples.

[0104] Step 2. Preprocessing the samples

[0105] Step 3. Extract structure feature matrix

[0106] Extract the direction features of the handwriting and the features of the space occupied by the characters, and the obtained matrix 1≤i≤N j}, 1≤j≤C} is the original feature matrix set, where Represents the original feature matrix extracted from the i-th sample belonging to the j-th category, N j Indicates the number of samples of the jth category, and C indicates th...

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 on-line handwritten Tibetan language recognition method and a recognition system. The on-line handwritten Tibetan language recognition method comprises the following steps of: carrying out pretreatment on a handwritten character mode; extracting the direction features of handwriting points and the features of the space occupied by the characters, and carrying out dimensionality reduction and switching on a higher-dimension feature through a linear discriminating analysis method, thus obtaining the recognition features of the Tibetan language characters; improving the speed of a standard quadratic classifier and obtaining a high-speed quadratic classifier which is used for recognizing the Tibetan language characters; associating the syllables with the recognized characters; and finally inputting the standard Tibetan language syllables into the text. The invention finishes an integral on-line handwritten Tibetan language recognition system through the pretreatment on the Tibetan language characters, feature extraction, classifier designing and syllable association. The on-line handwritten Tibetan language recognition method and the recognition system can be used in the on-line handwritten Tibetan language recognition inputting in computers and mobile phones, and has the advantages of high recognition rate, high inputting speed, steady performance, and the like.

Description

technical field [0001] The invention relates to the field of on-line handwritten character recognition for Chinese information processing; in particular, it relates to a method and a recognition system for on-line handwritten Tibetan character recognition. Background technique [0002] Online handwriting input, as a natural input method, has been widely used due to the improvement of pen input devices. The research on online handwritten Chinese character recognition in my country began in the 1980s. Through the unremitting efforts of many researchers, the online handwritten Chinese character recognition technology has made great progress, and practical products are constantly appearing on the market. The informatization of minority languages ​​and related research is relatively lagging behind. Up to now, there have been no relevant reports on methods involving online handwritten Tibetan recognition. However, it is of great theoretical and practical significance in the appli...

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): G06K9/20G06K9/72
Inventor 王维兰
Owner NORTHWEST UNIVERSITY FOR NATIONALITIES
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