Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems
This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and accele...
Saved in:
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and acceleration. The offline features include pixel density, centre of gravity, distance and angle. All features considered are local in nature Two analysis techniques are considered - ANOVA based and Equal Error rate (EER) based. Experimental results show that all online features have a high distinguishing capability while for the offline case, angle and distance are good for distinguishing between genuine and skilled forgeries for an HMM based signature verification system while pixel density and centre of gravity are not. � 2008 IEEE. |
|---|