Off-line Handwritten Signature Verification System: Artificial Neural Network Approach

Nowadays, it is evident that signature commonly used for personal verification, this justifies the necessity an Automatic Verification System (AVS). Based on application, verification could either be achieved Offline or Online. An online system uses signature’s dynamic information; such information captured at instant generated. offline system, other hand, image (the scanned). In paper, some set of simple shaped geometric features are in achieving signatures. These include Baseline Slant Angle (BSA), Aspect Ratio (AR), and Normalized Area (NA), Center Gravity as well line’s Slope joins Gravities two splits. Before extraction, a preprocessing necessary to segregate its parts eliminate any available spurious noise. Primarily, training via record which was acquired from personalities whose signatures had validated through system. average each subject result incorporating aforementioned were derived sample subject’s true Therefore, functions prototype authentication against requested test signature. The similarity measure within feature space between determined by Euclidian distance. If distance lower than threshold (i.e. analogous minimum acceptable degree similarity), certified claiming otherwise detected forgery. Details stated features, pre-processing, implementation, results presented work.