Handwritten Signature Forgery Detection using Convolutional Neural Networks

被引：11

作者：

Gideon, Jerome S. ^{[1
]}

Kandulna, Anurag ^{[1
]}

Kujur, Aron Abhishek ^{[1
]}

Diana, A. ^{[1
]}

Raimond, Kumudha ^{[1
]}

机构：

[1] Karunya Inst Technol & Sci, Dept Comp Sci Technol, Coimbatore 641114, Tamil Nadu, India

来源：

8TH INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING & COMMUNICATIONS (ICACC-2018) | 2018年 / 143卷

关键词：

Signature Forgery Detection; Convolutional Neural Networks; Machine Learning; Deep Learning;

D O I：

10.1016/j.procs.2018.10.336

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Handwritten signatures are very important in our social and legal life for verification and authentication. A signature can be accepted only if it is from the intended person. The probability of two signatures made by the same person being the same is very less. Many properties of the signature may vary >even when two signatures are made by the same person. So, detecting a forgery becomes a challenging task. In this p-aper, a solution based on Convolutional Neural Network (CNN) is presented where the model is trained with a dataset of signatures, and predictions are made as to whether a provided signature is genuine or forged. (C) 2018 The Authors. Published by Elsevier B.V.

引用

页码：978 / 987

页数：10