Off-Line Signature Verification Based on Multi-Feature Fusion and Neural Network

Aiming at less information available in off-line signature, the accuracy of using a single character to verify is not high enough, an off-line handwritten signature authentication method based on multi-feature fusion is presented. At first, ET1DT12 feature and moment feature are extracted from the same signature and combined to form a new high-dimensional feature, then RBF neural network is used for training and verification. Experimental results show that the method can effectively improve the accuracy of off-line signature verification.