Scribd
Upload
39 views

Batch 10 Signature Verification

This document outlines a student project on signature verification using image processing. The project aims to accurately detect forged signatures using a neural network approach. The proposed solution is to use a backpropagation neural network trained on preprocessed signature images to classify signatures as genuine or forged. Key steps include preprocessing signatures, extracting features, training the neural network, and verifying new signatures with the trained model. The project will use Google Colab for implementation and references several papers on offline signature verification techniques.

Uploaded by

Kundeti Vennela
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
39 views

Batch 10 Signature Verification

This document outlines a student project on signature verification using image processing. The project aims to accurately detect forged signatures using a neural network approach. The proposed solution is to use a backpropagation neural network trained on preprocessed signature images to classify signatures as genuine or forged. Key steps include preprocessing signatures, extracting features, training the neural network, and verifying new signatures with the trained model. The project will use Google Colab for implementation and references several papers on offline signature verification techniques.

Uploaded by

Kundeti Vennela
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Signature Verification Using Image Processing

Batch-10

Team Members:
19B01A04H3 – T.Niharika
19B01A04E6 – D.Anusha
19B01A04H4 –
T.Bhagyasri

Guided by:
Ms.T.Pavani Varma
Assistant
Professor

Department of Electronics and


Contents

 Motivation
 Objective
 Project Background
 Literature Survey
 Problem Identification
 Proposed Solution and Implementation
 Block Diagram
 Tools Required
 References
Motivation

 Nowadays, person identification and verification is very important security


and resource access control.

 Among the different forms of biometric verification system signature will be


most
widely used.

 For any legal transcations the authorization is done by the signature. So the need
of the signature verification increases.
Objective

 To make sure that only the right people are authorized to access high-
security systems.

 The process of signature verification should be able to detect forgeries.

 To use cascading of features for the process of feature extraction of


signature from the preprocessed scanned image of a signature that will give
more accurate results.
Project Background

Back Propagation Neural Network (BPNN):

 Back propagation algorithm in machine learning is fast, simple and easy to program.

 Back propagation is the essence of neural network training

 Training of BPNN, this involves developing a suitable neural network model (BPNN).
Then the extracted features are presented to BPNN, which recognizes the different types
of signature images. The training takes place such that the neural network learns that each
entry in the input file has a corresponding entry in the output file.
Literature Survey

Title Offline Handwritten Signature Recognition

Author Gulzar A. Khuwaja; Mohammad S. Laghari

Journal Name zenodo.org on November 25, 2011

Work Biometrics, which refers to identifying an individual based


on his or her physiological or behavioral characteristics,
has the capability to reliably distinguish between an
authorized person and an imposter
Results This paper presents a neural network based recognition
of offline handwritten signatures system that is trained
with low- resolution scanned signature images.
Drawbacks Accuracy is very low
Problem Identification

 Nowadays illegal transcations are happening in large scale due to forgery of signatures in banking
and business sectors.

 Signature verification is a technology that can improve security in our day to day transaction held
in society.

 To increase accuracy in signature verification so that there will be no rise of problems in different
sectors likes banking and financial.
Problem Solution and Implementation
The Proposed solution is to use deep learning techniques to verify the signature of the
person.

Implementation:
Input: Training sample images.
Output: Construction of Signature verification system using BPNN.

Read the training samples images.


Step1: Pre-processing
 Convert the image into gray scale image.
 Convert the gray scale image into binary image.
 Apply thinning process.
 Apply bounding box.
Step2: Features Extracted.
Step3: Back propagation neural network training.
Block Diagram

Preprocessing & Verification


Signature Entered Verification by Result (Genuine
Feature
by User using stored value or Forged)
Extraction
Software Tools Required

 Google Colab Notebook


References

1. J. F. Vélez, Á. Sánchez , and A. B. Moreno, “Robust Off-Line Signature Verification Using Compression
Networks And Positional Cuttings”, Proc. 2003 IEEE Workshop on Neural Networks for Signal Processing, vol.
1, pp. 627-636, 2003

2. https://https://youtu.be/1k6kA7lQY_w

3. https://ijircst.org/DOC/27_irp366728255fa-1a7d-4123-a99b-3a4ba558ba43.pdf

4. Ramachandra A. C ,Jyoti shrinivas Rao”Robust Offline signature verification based on global features” IEEE
International Advance Computing Conference ,2009.

You might also like