Offline Signature Verification System Using Energy on Grid Level

Signature is a behavioral biometric. One’s signature may change over time and it is not nearly as unique or difficult to forge as iris patterns or fingerprints, however signature’s widespread acceptance by the public, make it more suitable for certain lower-security authentication needs. Signature verification is split into two according to the available data in the input, Off-line and On-line. In this work we present offline signature verification system. Offline signature verification is difficult to design as many desirable characteristic such as order of strokes, the velocity and other dynamic information are not available in the offline. Although difficult to design, offline signature verification is crucial for determining the writer identification. In this proposed method we evaluate energy of signature on grid level as features. For this we have taken 5 genuine signatures for training and extract their features and stored as training features. Now for each writer we have taken 5 testing genuine signature and extracted their energy features and this features are compared with stored training feature of each writer using different distance metrics and we have find the best distances for energy features.