Kokubunji, Tokyo, Japan
Oct. 26, 2004 to Oct. 29, 2004
ISBN: 0-7695-2187-8
pp: 498-502
Edson J. R. Justino , Pontif?cia Universidade Cat?lica do Paran?
Cesar Santos , Pontif?cia Universidade Cat?lica do Paran?
Robert Sabourin , ?cole de Technologie Sup?rieure
In an off-line signature verification method based on personal models, an important issue is the number of genuine samples required to train the writer?s model. In a real application, we are usually quite limited in the number of samples we can use for training (4 to 6). Classifiers like the Neural Network [5], the Hidden Markov Model [2] and the Support Vector Machine [1] need a substantial number of samples to produce a robust model in the training phase. This paper reports on a global method based on only two classes of models, the genuine signature and the forgery. The main objective of this method is to reduce the number of signature samples required by each writer in the training phase. For this purpose, a set of graphometric features and a neural network (NN) classifier are used.
Signature verification, Expert?s classifier, Neural network.
Edson J. R. Justino, Cesar Santos, Robert Sabourin, "An Off-Line Signature Verification Method Based on the Questioned Document Expert?s Approach and a Neural Network Classifier", IWFHR, 2004, Ninth International Workshop on Frontiers in Handwriting Recognition, Ninth International Workshop on Frontiers in Handwriting Recognition 2004, pp. 498-502, doi:10.1109/IWFHR.2004.17