VERIFICATION OF SIGNATURE
Project Members 1) Sakshi Jadhav
2) Nikita Jadhav
3) Vaishnavi Sonawane
4) Neha Pagariya
Guided By: A. A. Pawar Sir
Hod: Prof . P. G. Sali sir
Project Co-Ordinator: Ms . S. S. Shinde Mam
AIM :-
• The aim of signature verification is to classify the input
signature as genuine or forgery by matching it against the
database signature image using some distance measure.
• Forgery means that an individual is trying to make false
signatures of any other individual to become authenticated.
OBJECTIVES :-
• Information about the way the human hand creates the
signature such as hand speed and pressure measurements,
acquired from special peripheral units, is needed.
• A signature recognition and verification is a system capable of
efficiently addressing two individual but strongly related tasks
identification of the signature owner, and , decision whether the
signature is genuine or forger.
ABSTRACT:-
Signatures are widely used as a means of personal
identification and verification. Many documents like bank cheques
and legal transactions require signature verification. Signature-
based verification of a large number of documents is a very difficult
and time consuming task.
.
INTRODUCTION:-
The authenticity of many legal, financial, and other documents is
done by the presence or absence of an authorized handwritten
signature. “Digital Signature” is the best solution for authenticity
in various fields. A digital signature is nothing but an
attachment to any piece of Python Based information, which
represents the content of the document for that document. Now
days , many fraud things happens if any unknown person wants
to imitate person’s identity. If a person sign name of the checking
account holder to check without account holder’s permission,
then this is considered signature forgery
LITERATURE SURVEY:-
Year of
Sr No Paper Name
Publication
1) Handwritten signature 2020
verification using shallow
Convolutional Neural Network
2) Signature verification using 2019
Convolutional Neural Network
SYSTEM ARCHITECTURE:-
METHODOLOGY:-
In this project,
Er Diagram:-
DFD Diagram Level 0 :-
DFD Level 1 Diagram :-
HARDWARE & SOFTWARE
REQUIREMENT:-
I. Hardware Requirement
i. Laptop or PC
Windows 7 or higher
I5 processor system or higher
8 GB RAM or higher
100 GB ROM or higher
50 GB SSD
I. Software Requirement
i. Laptop or PC
• Spyder(2.7 or above)
• MYSQL
ADVANTAGE:-
• Signature is a man-made biometric system where forgery has
been studied extensively.
• Forgery is detected even when the forger has managed to get a copy
of the authentic signature.
• The signature verification system is independent of the native
language user.
• Cheap hardware.
• Little storage requirements.
DISADVANTAGE:-
• The private key must be kept in a secured manner.
• The process of generation and verification of digital signature
requires considerable amount of time.
• For using the digital signature the user has to obtain private and
public key, the receiver has to obtain the digital signature certificate
also.
CONCLUSION:-
In this project , simple and effective convolutional neural network-
based language-independent signature verification architecture has
been purposed. The purposed model is quite simple in terms of the
number of basic layers (Conv & Pool) contrary to the other state art
methods; hence the weight parameters to be optimized are lesser in
number .
REFERENCES:-
• Devnath , L. & Islam, Md. R. (2016). Off-line human signature recognition system
based on histogram analysis using MATLAB.
• Kumar, D. A. & Dhandapani, S. (2016). A novel bank check signature verification
model using concentric circle masking features and its performance analysis over
various neural network training functions.
• Salama, M. A. & Hussein, W, (2016). Invariant directional feature extraction and
matching approach for robust offLine signature verification.
