A new stroke extraction method for handprinted Chinese character recognition

Pao Yue-kong Library Electronic Theses Database

A new stroke extraction method for handprinted Chinese character recognition

 

Author: Tam, Tai-cheung
Title: A new stroke extraction method for handprinted Chinese character recognition
Degree: M.Sc.
Year: 1997
Subject: Chinese language -- Data processing
Chinese character sets (Data processing)
Input design, Computer
Information storage and retrieval systems
Hong Kong Polytechnic University -- Dissertations
Department: Dept. of Electronic Engineering
Pages: viii, 88, [25] leaves : ill. ; 30 cm. + computer disk
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1420185
URI: http://theses.lib.polyu.edu.hk/handle/200/200
Abstract: In this project, a great deal of literature study and survey in the areas of handprinted Chinese character processing and recognition had been carried out. The knowledge and experience of the researchers in these areas are absorbed and hence a simple but effective handprinted Chinese character stroke extraction and recognition system is aimed to be devised and developed. The algorithms developed are attempted to be simple enough that they can be implemented on embedded microcontroller systems for postage address recognition and discrimination. The database of reference character library therefore need not be too large. So, the first 1,000 characters in the Eten 24 x 24 pixels font were chosen for testing. At first, an algorithm is developed to extract strokes without carrying out the thinning process because almost all thinning algorithm would cause spurious branches, splitting of the cross-point or distortion around junctions. It performs quite well for restricted handprinted characters, i.e. characters with clear separable strokes. But its performance is not good for unrestricted or distorted characters. Later on, strokes are thinned before extraction. To do that, a simple thinning method is employed and modification is made specially for Chinese characters. A stroke extraction algorithm is also developed for stroke segmentation and

Files in this item

Files Size Format
b14201859.pdf 3.020Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information