Scribd
Upload
38 views7 pages

PY094

This is the minimum amount of the amount of money to pay the amount of money in your account transfer hota to the legend of the day of the day of the

Uploaded by

kashyapsaurav7765
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
38 views7 pages

PY094

This is the minimum amount of the amount of money to pay the amount of money in your account transfer hota to the legend of the day of the day of the

Uploaded by

kashyapsaurav7765
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 7

Signature Verification System Using CNN

1) Background/ Problem Statement

Every person has a unique signature that is used primarily for personal
identification and verification of important documents or legal
transactions. Mostly used to authenticate checks, draughts, certificates,
approvals, letters, and other legal documents. Because a signature is
used in such critical activities, verification of its authenticity is essential.
This type of verification is critical in preventing document forgery and
falsification in a variety of financial, legal, and commercial settings.
Traditionally, signatures were manually verified by comparing them to
copies of genuine signatures. This simple method may not be sufficient
as technology advances, bringing with it new techniques for forgery and
falsification of signatures.
So, in order to tackle such a problem new efficient tool is needed. Our
Signature Verification System can help in the authentication of a
handwritten signature by reducing human error.
2) Working of the Project

Our python-based Signature Verification System consists of 1 module:


User.

The user would need to sign in using their basic information to log in. To
verify a signature, the user would need to fill in two images, one will be
the original image, and the second will be the comparison image. Once
the images are filled in, the user will be directed to the results page to
see the results.

For the purpose of classifying the signature classification model, we


have implemented a machine-learning model. We will use CNN for this.
To test and see the results, we will take a sample signature (about 100
sample pictures of the same signature) and compare the sample
pictures of the original signature with other random signatures.

The framework used in this project is Django. The Front End involves
Html, CSS and JavaScript. The Back End involves MySQL Database. The
Back End Language is Python.
3) Advantages

The system is easy to maintain.


It is user-friendly.
It automatically detects without any human supervision.
A simple and effective method for identifying a person's signature.
4) System Description

The system comprises 2 major modules with their sub-modules as


follows:

 USER:

● Sign In:

The user would need to sign in using their: Name, Number, Email,
Password, Username, Photo and Age.

● Login:

The user can log in after signing in.

● Start Matching:

The user will fill in two images, one will be the original image, and
the second will be the comparison image.
The system will direct users to the results page to see the results.
5) Project Life Cycle

The waterfall model is a classical model used in the system


development life cycle to create a system with a linear and sequential
approach. It is termed a waterfall because the model develops
systematically from one phase to another in a downward fashion. The
waterfall approach does not define the process to go back to the
previous phase to handle changes in requirements. The waterfall
approach is the earliest approach that was used for software
development.
6) System Requirements

I. Hardware Requirement

i. Laptop or PC
 Windows 7 or higher
 I3 processor system or higher
 4 GB RAM or higher
 100 GB ROM or higher

II. Software Requirement

ii. Laptop or PC
 Python
 Sublime text Editor
 XAMP Server
7) Limitations/Disadvantages

Image quality has an impact on signature recognition.


There's a possibility it won't be able to identify the signature if the
background lighting is dim.

8) Application

This system can instantly determine whether a person's signature


is real or fake.

9) Reference
 https://www.researchgate.net/publication/
283556955_Signature_verification_using_Java_-
_Python_for_small_computational_devices
 https://www.researchgate.net/publication/351322176_A_Review_-
_Signature_Verification_System_Using_Deep_Learning_A_Challenging_Pro
blem
 https://www.researchgate.net/publication/
337084834_Offline_Signature_Verification_Using_Convolutional_Neural_N
etwork_Undergraduate_Project_Subject_Code_CT_707
 https://www.ijcrt.org/papers/IJCRT2205942.pdf

You might also like