TY - GEN
T1 - Optimal threshold selection for online verification of signature
AU - Alizadeh, A.
AU - Alizadeh, T.
AU - Daei, Z.
PY - 2010
Y1 - 2010
N2 - In this paper an innovative method for 1verification of signature using parametric features based on optimal threshold selection is proposed. For each signature, 62 parametric feature are derived from horizontal place, x(t), vertical place, y(t) and pen down and up signals which are obtained from a digitizer plane. The weighted distance between each feature of a signatories and the related reference features is compared to a suitable threshold value and then the feature is accepted or not. The number of the accepted features for a person is then compared to another threshold, which has a suitable value for each signature, and then the signature will be verified or rejected. In this research, 1500 original signatures from 30 person and 600 forgery signatures are used. For each person, 30 genuine and 10 forgery signatures are considered for training of the algorithm and the rest are used in testing and validation. It is shown in the results that there is 0.67% false rejection ratio and 0.67% false acceptation ratio for the training set and a 2.68% and 1.99% for the testing set, respectively.
AB - In this paper an innovative method for 1verification of signature using parametric features based on optimal threshold selection is proposed. For each signature, 62 parametric feature are derived from horizontal place, x(t), vertical place, y(t) and pen down and up signals which are obtained from a digitizer plane. The weighted distance between each feature of a signatories and the related reference features is compared to a suitable threshold value and then the feature is accepted or not. The number of the accepted features for a person is then compared to another threshold, which has a suitable value for each signature, and then the signature will be verified or rejected. In this research, 1500 original signatures from 30 person and 600 forgery signatures are used. For each person, 30 genuine and 10 forgery signatures are considered for training of the algorithm and the rest are used in testing and validation. It is shown in the results that there is 0.67% false rejection ratio and 0.67% false acceptation ratio for the training set and a 2.68% and 1.99% for the testing set, respectively.
KW - Feature extraction
KW - Online signature verification
KW - Parametric features
KW - Weighted Euclidean distance
UR - http://www.scopus.com/inward/record.url?scp=79952404986&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79952404986&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:79952404986
SN - 9789881701282
T3 - Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
SP - 98
EP - 102
BT - Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
T2 - International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
Y2 - 17 March 2010 through 19 March 2010
ER -