Centre of Excellence in Cognitive Science - CECoS

College of Research Methodology and Cognitive Science (RMCS), Burapha University

 

  Home   Event    People    Research   Project  ○  Publication  ○  Collaboration  ○  Contact Us

 

Senior engineering projects done in 2010

Senior engineering projects done in 2009

Senior engineering projects done in 2008

Copyright © All rights reserved.

 

" User Authentication using Online Handwriting Recognition via Touchscreen "

Project Team: Rungrot Saetan and Komson Sookmuang

URL: http://www.rmcs.buu.ac.th/cecos/project/touch (Thai)

Problem: Due to the importance of biometric system in our daily life, the secure system uses physiological and behavioral traits for uniquely recognizing humans/users. In practice, there are many biometric systems that can be realized based on physiological and behavioral for examples, fingerprint, face recognition, DNA, hand and iris recognition, typing rhythm, gait, and voice. However, each one has different characteristics in terms of user's purpose such as ease of use, error incidence, accuracy, user acceptance, required security level, and long-term stability, and system cost.

Basic Idea: This project proposes a simple identifying method for the applications of user authentication based upon handwriting recognition. The proposed system can be applied as the biometric system in which the users can write/sign any style they want via the touchscreen technology.

 

Process diagram of the proposed method

 

Method: The primitive chain code (PCC) and XY projection method were used as the input parameters. To verify whether handwriting of user is correct, this project applied correlation coefficient and conditional probability as the decision values. We have implemented all these processes on ARM7TDMI-S LPC2138 MCU 16/32-Bit processor, 3.2" TFT LCD touchscreen with resolution 240x320 pixels.

Example of primitive chain code (PCC) in this project

 

XY projection method

 

Example of individual handwritten character via touchscreen

 

   

ZIGN, Real assembled device

 

Experimental Results: We named this authentication system as “ZIGN”. First group of sample students at Burapha University in related fields of technology (5 male, 5 female) and second group in non-related fields of technology (5 male and 5 female) volunteered in this experiment. The results show that the average percentages of accuracy rate of 71% and classification rate of 100%. The ZIGN supports many applications; individual online signature recognizer, simple online OCR, handwritten characters recognizer, for examples.

Publication: In preparation.

 

 

Copyright © 2009-11 CECoS, College of Research Methodology and Cognitive Science, Burapha University, Chonburi 20131 Thailand.