Feature selection for off-line recognition of different size signatures

G.D.D.C. Cavalcanti1, R.C. Doria1, E.Cde.B.C. Filho1
1Centro de Informática, Universidade Federal de Pernambuco, Recife, Pernambuco, Brazil

Tóm tắt

The aim of this work is to select a set of features, which have good performance to solve the problem of signature recognition of different sizes. The signature database was formed for three sizes of signatures per user, small, median and big. This study uses structural features, pseudo-dynamic features and five moment groups. The feature selection method chosen is the one that select the best individual features based on classifiers like Bayes and k-NN.

Từ khóa

#Spatial databases #Handwriting recognition #Feature extraction #Data analysis #Data mining #Cameras #Forgery

Tài liệu tham khảo

doria, 2001, How distortions in different size signatures influence moment based techniques, PRIP Conf, 1, 219 10.1016/S0952-1976(00)00064-6 10.1109/ICDAR.1997.620566 10.1109/34.506799 10.1109/PROC.1979.11309 10.1016/0031-3203(93)90098-H 10.1016/S0031-3203(98)00141-1 10.1109/34.574797 10.1016/S0031-3203(96)00063-5 10.1016/S0031-3203(96)00059-3 10.1016/0031-3203(92)90135-6 ammar, 1986, A New Effective Approach for Off-line Verification of Signatures by using Pressure Features, 8th ICPR, 566