Computerized handwriting evaluation system for handwriting difficulty

Pao Yue-kong Library Electronic Theses Database

Computerized handwriting evaluation system for handwriting difficulty


Author: Wong, Hoi-cheung Louis
Title: Computerized handwriting evaluation system for handwriting difficulty
Degree: M.Sc.
Year: 2008
Subject: Hong Kong Polytechnic University -- Dissertations
Writing -- Identification -- Data processing
Chinese language -- China -- Hong Kong -- Writing.
Students -- China -- Hong Kong -- Writing
Department: Dept. of Health Technology and Informatics
Pages: xiv, 95 leaves : ill. (some col.) ; 30 cm.
InnoPac Record:
Abstract: In Chinese culture, using correct stroke orders and creating a suitable character layout is one of a major concern in handwriting. Character layout refers to the outlook of the character, and having best character layout is equivalent to pleasurable legibility. Stroke order refers to the writing sequence of each stroke that forms the desire character, and stroke order is one special characteristic of the Chinese word. Able to write a character with correct stroke orders together with a layout that follows the specific proportionality of the character are regarded as two of the major qualities that makes good Chinese handwriting. Besides, teaching children to attaint good handwriting skills is an important learning goal in primary school education. Inversely, children with poor handwriting often produce written scripts that are difficult to read and may be misinterpreted as incorrect. This affected their perfonnance in compositions and other written tasks that are required in their studies. In literature, it has been reported that 11-12% of female students and 21-32% of male students have handwriting difficulties. To help these students, there is a need for handwriting evaluation systems that can identify individuals with handwriting difficulties, so that proper intervention can be conducted as early as possible. There are a number of computerized software packages available on the market that claim to provide handwriting evaluation. Unfortunately, they are not designed to handle Chinese Characters. Therefore, it is necessary to develop a new system for Chinese handwriting evaluation. In this work, a new Chinese handwriting evaluation system was designed based on the Online Chinese Character Recognition (OLCCR) logic. OLCCR is a method to recognize handwriting character (particularly for whole character recognition) by capturing the real time digitized writing input. To evaluate the character outlook, a scoring method was used to rank the neatness of the character based on inputs from experienced Chinese subject teachers. To evaluate the efficacy of the system, twenty students aged from seven to nine were recruited to participate in the handwriting assessment. Ten of them were identified of having handwriting difficulties and ten were classified as having "good" handwriting skills. Each participant were requested to write a number of pre-selected Chinese characters on a digital writing broad using an inked pen, and the hardcopies of their handwriting were evaluated and rated by three teachers. Two sample T test was used to compare the outcome scores on handwriting from the newly developed system with the scores assigned by the teachers. The result demonstrated the system was able to differentiate between proficient and poor handwriter with statistical significant (p<0.05). Further, on stroke analysis, students of the proficient group had 26% of incorrect strokes during writing, whereas for those students having handwriting difficulties, much more incorrect strokes were found (56%).

Files in this item

Files Size Format
b23530613.pdf 8.515Mb 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


More Information