DocumentCode :
2961740
Title :
Analysis of off-line handwritten text samples of different gender using shape descriptors
Author :
Sokic, Emir ; Salihbegovic, Almir ; Ahic-Djokic, M.
Author_Institution :
Dept. for Autom. Control & Electron., Univ. of Sarajevo, Sarajevo, Bosnia-Herzegovina
fYear :
2012
fDate :
25-27 Oct. 2012
Firstpage :
1
Lastpage :
6
Abstract :
The human experience in the analysis of the handwriting of male and female writers indicates that gender affects the appearance of the handwritten text. These differences are usually very difficult to describe numerically. In order to analyze the handwriting differences between male and female writers, several shape description techniques, such as the tangent angle function, curvature function and Fourier descriptors, were used in this paper. As an additional contribution of the paper, a database of 3766 off-line handwritten cursive and capitalized written words has been created. The database consists of male and female handwriting samples, classified by gender and handedness. The experimental results show that typical attributes of male and female handwritings imply certain differences in shape decriptors, and those differences have the potential for usage in gender handwriting discrimination.
Keywords :
handwriting recognition; Fourier descriptors; capitalized written words; curvature function; female writers; gender handwriting discrimination; handwriting differences; handwriting samples; off-line handwritten cursive words; off-line handwritten text samples; shape decriptors; shape description techniques; shape descriptors; tangent angle function; Databases; Feature extraction; Humans; Image segmentation; Shape; Transforms; Writing; database; gender identification; handwriting; shape descriptors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Telecommunications (BIHTEL), 2012 IX International Symposium on
Conference_Location :
Sarajevo
Print_ISBN :
978-1-4673-4875-1
Electronic_ISBN :
978-1-4673-4874-4
Type :
conf
DOI :
10.1109/BIHTEL.2012.6412086
Filename :
6412086
Link To Document :
بازگشت