Name
Abstract | ||
|---|---|---|
In this paper a new method for on-line signature authentication will be presented, which is based on a event-string modelling of features derived from pen-position and pressure signals of digitizer tablets. A distance measure well known from textual pattern recognition, the Levenshtein Distance, is used for comparison of signatures and classification is carried out applying a nearest neighbor classifier. Results from a test set of 1376 signatures from 41 persons are presented, which have been conducted for four different feature sets. The results are rather encouraging, with correct identification rates of 96% at zero false classifications. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ICPR.2004.965 | ICPR (2) |
Keywords | Field | DocType |
digitizer tablet,levenshtein distance,different feature set,nearest neighbor classifier,event-string modelling,pressure signal,on-line signature authentication,distance measure,new method,correct identification rate,pattern recognition,handwriting recognition | Authentication,Pattern recognition,Computer science,Handwriting recognition,Levenshtein distance,Speech recognition,Feature (machine learning),Artificial intelligence,Nearest neighbor classifier,Test set | Conference |
ISSN | ISBN | Citations |
1051-4651 | 0-7695-2128-2 | 22 |
PageRank | References | Authors |
1.23 | 4 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sascha Schimke | 1 | 47 | 4.47 |
| Claus Vielhauer | 2 | 461 | 68.50 |
| Jana Dittmann | 3 | 1416 | 221.92 |