Handwritten Uighur word segmentation identification method

A recognition method and word technology, applied in the field of handwriting recognition, can solve the problems that the preprocessing technology is not easy to get the best effect and affects the segmentation effect, etc.

Active Publication Date: 2018-11-06
XINJIANG UNIVERSITY
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Special preprocessing techniques such as tilt correction, baseline position detection and additional stroke detection are not easy to get the best results, thus affecting the segmentation effect

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 Uighur word segmentation identification method
  • Handwritten Uighur word segmentation identification method
  • Handwritten Uighur word segmentation identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0107] If the overall shape of a Uyghur word and the individual letters it contains are written according to the rules, word segmentation can be handled conveniently by implementing explicit segmentation methods. However, the handwriting process often does not obey various writing rules, and the same letter or word is completed with various styles and writing sequences. Therefore, the implicit segmentation method of dynamically searching segmentation points is a natural choice for handwritten word segmentation research. Although handwriting samples vary in shape, there should be some common properties that make them correct and readable. Individual letters in handwritten words can always be segmented with some information points. It is common to write different letters together in the handwriting process of Uyghur words, which increases the difficulty of the word segmentation task.

[0108] Although Uyghur and Arabic have many similar letters, the Uyghur character segmentati...

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 relates to a handwritten Uighur word segmentation identification method, belongs to the handwritten form identification field, is particularly suitable for word segmentation of handwritten Uighur words on mobile terminals and aims to solve a technical problem of providing a word segmentation method utilizing the local information of the handwritten trajectory without delayed stroke pre-detection. The method comprises steps of preprocessing; local information point detection of the trajectory; detection of straight points, local maximum point / peak points, local minimum point / valley points, local rightmost points, local leftmost points, intersection points and starting points and ending points of strokes in the handwritten trajectory; word over-segmentation based on the trajectory local information points; segmentation block merging; segmentation block combination for forming letters. The method is advantaged in that stroke pre-delay processing is not needed, so processingis faster, high universality is realized, and the method is suitable for segmentation of the natural handwritten words.

Description

technical field [0001] The invention belongs to the field of handwriting recognition, and is particularly suitable for a recognition method for word segmentation of handwritten Uighur words on a mobile terminal. Background technique [0002] Handwriting recognition is one of the widely used branches in the field of pattern recognition. There are two types of handwriting recognition, one is the online handwriting recognition technology for recognizing the handwriting track recorded in real time, and the other is the recognition technology for handwriting style images, that is, the off-line handwriting recognition technology. The implementation methods of handwriting recognition are different for different languages ​​or characters. Letters in some texts are units of meaning, such as Chinese. For handwriting recognition where letters are meaning units, it mainly recognizes all the letters it contains, and the number of commonly used letters is limited. It is entirely possibl...

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): G06K9/00G06K9/34G06K9/40
CPCG06V30/32G06V30/153G06V10/30
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