Title :
Using calligraphies features for off line writer identification
Author :
Vasquez, Jose Luis ; Travieso, Carlos M. ; Alonso, Jesus B.
Author_Institution :
Sede del Atlantico, Univ. of Costa Rica, Cartago, Costa Rica
Abstract :
This work proposes an off-line writer identification approach based on graphometrical and forensic features. We selected a set of features with independence of the text and some stability degree to natural changes in the writing. The system uses the LS-SVM classifier with RBF kernel, reaching up to 99.1% of success rate for an own database composed by 100 users with 10 samples per each one.
Keywords :
feature extraction; handwriting recognition; least squares approximations; radial basis function networks; support vector machines; LS-SVM classifier; RBF kernel; calligraphy features; forensic feature; graphometrical feature; least squares support vector machines; offline writer identification; radial basis function kernel; stability degree; Databases; Educational institutions; Feature extraction; Forensics; Support vector machines; Training; Writing; Biometrics; Graphology Techniques; Off-line Handwriting; Patter Recognition; SVM; Writer Identification;
Conference_Titel :
Security Technology (ICCST), 2013 47th International Carnahan Conference on
Conference_Location :
Medellin
DOI :
10.1109/CCST.2013.6922062
