Handwritten Signature Verification System using machine Learning Approach

Information Technology

In the field of biometric, offline handwritten signature verification is most referenced procedure for authentication of a person during financial transaction. A signature is the “seal of approval” for verifying the approval of a person and remains the most preferred means of verification. This verification system mainly aims at verifying the discriminating the forged signature from the genuine signatures. In this work, Convolutional Neural Networks (CNN) have been used to learn features from the pre-processed genuine signatures and forged signatures dataset. The CNN used is inspired by Inception V1 architecture (GoogleNet). The architecture uses the concept of having different filters on same level so that the network would be wider instead of deeper. In this paper, the proposed model is tested on few publicly available datasets on kaggle.com. has been successful in verifying handwritten signature images provided with an extensive precision level.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.