Offline Signature Verification System for Bank Cheques Using Zernike Moments, Circularity Property and Neural Network

Handwritten signature is the most accepted and economical means of personnel authentication. It can be verified using online or offline schemes. This paper proposes a signature verification model by combining Zernike moments feature with circularity and aspect ratio. Unlike characters, signatures vary each time because of its behavioural biometric property. Signatures can be identified based on their shape. Moments are the good translational and scale invariant shape descriptors. The amplitude and the phase of Zernike moments, circularity and aspect ratio of the signature are the features that are extracted and combined for the verification purpose and are fed to the Feedforward Backpropagation Neural Network. This Neural Network classifies the signature into genuine or forged. Experimental results reveal that this methodology of combining zernike moments along with the two mentioned geometrical properties give higher accuracy than using them individually. The combination of these feature vector yields a mean accuracy of 95.83%. When this approach is compared with the literature, it proves to be more effective.