DEVELOPMENT OF AN AUTOMATED HANDWRITING ANALYSIS SYSTEM

In the present study a method has been proposed for the behavioral prediction of a person through automated handwriting analysis. The present work identifies the psychological traits in the writing namely size, slant and pressure, baseline, number of breaks, margins, speed of writing and spacing between the words. The handwriting is analyzed through Image Processing in MATLAB. The behavioral pattern of the person is predicted from the above traits of the handwriting. The developed system identifies handwriting closely which may not be possible for a graphologist. It is real time and involves less image preprocessing. The proposed system is calibrated with manual analysis. The results obtained through the system are in good agreement to more than 80 percent of the cases with ideal manual analysis.

[1]  Madasu Hanmandlu,et al.  Off-line signature verification and forgery detection using fuzzy modeling , 2005, Pattern Recognit..

[2]  Vivek Singh,et al.  Handwriting Analysis based on Segmentation Method for Prediction of Human Personality using Support Vector Machine , 2010 .

[3]  J Walton.  Handwriting changes due to aging and Parkinson's syndrome. , 1997, Forensic science international.

[4]  K. Anandakumar,et al.  Automated Human Behavior Prediction through Handwriting Analysis , 2010, 2010 First International Conference on Integrated Intelligent Computing.

[5]  Sung-Hyuk Cha,et al.  Individuality of handwriting: a validation study , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[6]  Horst Bunke,et al.  Writer identification using text line based features , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[7]  Jin H. Yan,et al.  Alzheimer's disease and mild cognitive impairment deteriorate fine movement control. , 2008, Journal of psychiatric research.

[8]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Thierry Paquet,et al.  Writer identification by writer's invariants , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[10]  Jau-Hwang Wang,et al.  Trace copy forgery detection for handwritten signature verification , 2003, IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings..