The traditional function of a signature is to permanently affix to a document in which a person’s uniquely personal, undeniable self-identification is used as physical evidence of that person’s personal witness and certification of the content of all, or a specified part of the document. One of the most important biometric authentication techniques is signature. Every person has his/her own signature which is unique and is used mainly for the purpose of personal identification and verification of important documents or legal transactions. There are two kinds of signature verifications. They are: static and dynamic. Static (off-line) signature verification is the process of verifying an electronic or document signature after it has been made by the person, while dynamic (on-line) signature verification takes place as a person creates his/her signature on a digital tablet or a device.
The main objective of human signature verification is to prevent signature fraud by malicious people. Online signatures have many distinctive features whereas offline signatures have lower distinctive features. So offline signatures are more difficult to verify. Offline signature verification is not very efficient and is slow for a large number of document verification.
The proposed system is to overcome the drawbacks of offline signature verification. We have proposed a Deep Learning (DL) based offline signature verification method using tensorflow to verify whether the signature is genuine or forged. The Deep Learning method used in our study is the Convolutional Neural Network (CNN). It is predicted that the success of the obtained results will increase if the CNN method is supported by adding extra feature extraction methods and classify successfully the human hand signature. After the completion of training and validation of the CNN model, the accuracy of the testing is checked.

Keywords: Signature, Deep learning, Tensorflow, CNN

PDF | DOI: 10.17148/IARJSET.2021.8856

Open chat