A Directional Feature with Energy based Offline Signature Verification Network

Signature used as a biometric is implemented in various systems as well as every signaturesigned by each person is distinct at the same time. So, it is very important to have a computerizedsignature verification system. In offline signature verification system dynamic features are not availableobviously, but one can use a signature as an image and apply image processing techniques to make aneffective offline signature verification system. Author proposes a intelligent network used directionalfeature and energy density both as inputs to the same network and classifies the signature. Neuralnetwork is used as a classifier for this system. The results are compared with both the very basic energydensity method and a simple directional feature method of offline signature verification system and thisproposed new network is found very effective as compared to the above two methods, specially for lessnumber of training samples, which can be implemented practically.