Online handwritten Uighur word tilt correction method

A tilt correction and word technology, applied in the field of handwriting recognition, can solve the problem of little research on handwritten word recognition, and achieve fast speed, good effect, and easy implementation.

Inactive Publication Date: 2018-11-30
XINJIANG UNIVERSITY
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, most of the work on Uyghur online handwriting recognition has focused on letter recognition, and there is little research on handwritten word 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
  • Online handwritten Uighur word tilt correction method
  • Online handwritten Uighur word tilt correction method
  • Online handwritten Uighur word tilt correction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The technical solution of the present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0035] 1 preprocessing

[0036] Preprocessing in online handwriting recognition technology generally includes normalization of handwriting trajectory, denoising and deduplication, smoothing and other operations. The preprocessing of handwritten word recognition for pinyin text also includes tasks such as baseline position detection and skew correction of handwritten word samples.

[0037] 1.1 Denoising

[0038] Due to the physical characteristics of the handwriting tablet and the writer's handwriting trembling during the handwriting process, distraction and other psychological and physiological factors, the collected online handwriting sample traces will have some noise. The general characteristics of these noise points are that they appear suddenly in the handwritten track and have a high degree of deviati...

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 online handwritten Uighur word tilt correction method, which adopts some basic preprocessing operations on Uyghur online handwritten word samples, including point insertion,multi-layer smoothing and point distance sampling. The method performs preprocessing in units of strokes in view of the fact that the basic pre-processing operation directly on the overall handwritten word track will generate additional noise or loses key information points. In order to solve the common tilt correction problem of handwritten words, the present invention proposes a tilt correctionalgorithm based on a block center. The algorithm is simple to implement, is fast in speed, and has a good tilt correction effect. The algorithm can be directly extended to handwritten words of otherpinyin texts and text line tilt correction.

Description

technical field [0001] The invention belongs to the technical field of handwriting recognition, and relates to a method for correcting the inclination of an online handwritten Uighur word, in particular to an inclination correction method for an online handwritten Uyghur word based on the center of gravity of a block track. Background technique [0002] Handwriting recognition is one of the main applications of pattern recognition. Like other pattern recognition tasks, research on handwriting recognition technology also includes preprocessing, feature extraction, model training and testing. Handwriting recognition technology research is divided into two categories, namely, online handwriting recognition technology and offline handwriting recognition technology. In online handwriting recognition, digitizers, such as handwriting boards, etc. are used during the handwriting process to identify handwriting styles on the handwriting tracks recorded in real time. Off-line handwr...

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): G06K9/32
CPCG06V30/1478
Inventor 艾斯卡尔·艾木都拉吾加合买提·司马义玛依热·依布拉音
Owner XINJIANG UNIVERSITY
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