Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Applying personalized weights to a feature set for on-line signature verification
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Hi-index | 0.00 |
The idea for the evaluation of class-dependent feature weights in verification problems is suggested. A scheme for non-exhaustive search based on the theory of experiment planning is used. The experiments carried out with a real signature based verification problem have shown an increase in the accuracy of up-to 1.7% for some classes.