Genuine and Forged Offline Signature Verification Using Back Propagation Neural Networks

---The need to make sure that only the right people are authorized to access high-security systems has paved the way for the development of systems for automatic personal authentication. Handwritten signature verification has been identified as a main contender in the search for a secure personal verification system. Signatures in offline systems are based on the scanned image of the signature. A new approach for offline signature verification is proposed and implemented. The proposed signature authentication system functions based on global and texture features of a given signature sample. This method makes use of the global features pulled out from the skeleton of the signature. While legitimate signatures of the same person may show some differences over a period, the differences between a skilled forgery and an actual signature may be imperceptible. When a genuine sample is given for enrollment, the system will automatically train the network with statistics generated from the given samples. The Back propagation network used verifies the global features for validity. The result is a gray level co-occurrence matrix representation of the signature sample, which is obtained from the picture matrix of spatial or texture features extracted. Based on the values obtained the network will decide the appropriateness of the signature. Keywords-Preprocessing, Feature Extraction, Global Features, Texture Features, False Acceptance Rate, False Rejection Rate.