Scribd
Upload
94 views18 pages

MINI PROJECT PPT SAMPLEpdf

The document discusses the development of a fake currency detection system using image processing and machine learning techniques to combat the rising issue of counterfeit banknotes. It highlights the need for automated systems in banks and ATMs, proposes a model that utilizes image processing for feature extraction, and presents results indicating 79% accuracy for genuine notes and 83% for counterfeit notes. Future enhancements include expanding to multiple currencies and improving accuracy with advanced algorithms.

Uploaded by

adilxrehman
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
94 views18 pages

MINI PROJECT PPT SAMPLEpdf

The document discusses the development of a fake currency detection system using image processing and machine learning techniques to combat the rising issue of counterfeit banknotes. It highlights the need for automated systems in banks and ATMs, proposes a model that utilizes image processing for feature extraction, and presents results indicating 79% accuracy for genuine notes and 83% for counterfeit notes. Future enhancements include expanding to multiple currencies and improving accuracy with advanced algorithms.

Uploaded by

adilxrehman
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/ 18

FAKE CURRENCY DETECTION USING IMAGE PROCESSING

Under the guidance of: Presented by:


Jataboina Hoyala Mohd Fazil Uz Zama(160921729031)
Assistant Professor Mohammed Samee Uddin(160921729003)
(CSE-AI&ML) Syed Murtuza Hussaini(160921729032)
Overview

01 Introduction 05 System Requirements 09 Conclusion


02 Abstract 06 Methodology 10 Future Scope
03 Existing System 07 Implementation
04 Proposed System 08 Result
Introduction
Increasing Issue of Forged Banknotes: The problem of counterfeit banknotes has significantly
escalated from the late 19th century to the 20th century, challenging the financial market due to the
high resemblance of fake notes to genuine ones.

Technological Challenges and Solutions: Advanced technology has made it easier for fraudsters to
produce convincing counterfeit notes, necessitating the development of systems to identify
forgeries, especially in banking and ATM machines.

Role of Artificial Intelligence and Machine Learning: AI and ML, particularly supervised machine
learning approaches, are critical in creating systems capable of distinguishing between genuine and
fake banknotes by analyzing image features.

Need for Automation in Currency Authentication: Developing an automated system to identify


counterfeit banknotes involves using image processing techniques to extract features from the notes
and applying SML algorithms to predict their authenticity.
Abstract
Prevalence of Fake Currency: During demonetization, a significant
amount of counterfeit currency was found in circulation,
highlighting the severity of the issue.

Identification Challenges: It is challenging for humans to


distinguish between genuine and forged banknotes due to the high
similarity in features, despite the parameters designed for
identification.

Need for Automated Systems: There is a necessity for automated


systems in banks and ATMs to accurately discriminate between
fake and genuine banknotes.

Algorithm Development: Designing an efficient algorithm capable


of predicting the authenticity of banknotes is crucial, as counterfeit
notes are created with high precision.
Existing System
Review of Machine Learning Approaches: Existing projects have reviewed
various machine learning approaches to classify the authenticity of DISADVANTAGES
banknotes.
•Accuracy is Low.
SVM Implementation:implemented Support Vector Machines (SVM) with
multiple kernels to reduce false rates, comparing the results with single-
kernel SVMs for classifying real and forged notes. •The technology is increasing very
vastly that will help the frauds to
generate fake note whose
Texture-Based Feature Extraction: Used a texture-based feature extraction resemblance is like genuine not and it
method and modeled texture using the Markov chain concept, allowing for is very difficult to discriminate them
the recognition of different countries' currencies. ion.

Global Optimization in ANN Training: Global optimization algorithms have


been applied during the training phase of Artificial Neural Networks
(ANNs), resulting in successful classification of forged and genuine notes.
Proposed System
Global Issue of Counterfeit Currency: Counterfeit currency
is a significant problem worldwide, impacting the
economies of many countries, including India, with
counterfeiters using advanced technology to evade
detection. ADVANTAGES
Need for Effective Detection Software: One of the most
effective solutions is the use of easily accessible and
efficient counterfeit detection software to combat • Accuracy is Very high.
counterfeiting.
• Classification of fake
Image Processing for Verification: The proposed system and original notes are
will utilize image processing technology to verify the very easy.
authenticity of currency notes by extracting distinguishing
features.

Focus on Accuracy and Speed: The success of the


software will be evaluated based on its accuracy and
speed, with an emphasis on identifying parameters that
can reliably differentiate between genuine and counterfeit
notes.
Advantages of Proposed System

• Accuracy is Very high.

• Classification of fake and original notes are very easy.


System Architecture
System Requirements

HARDWARE
SOFTWARE
REQUIREMENTS:
System : Pentium IV 2.4 GHz.
REQUIREMENTS:
Hard Disk : 40 GB.
Floppy Drive : 1.44 Mb.
Monitor : 14’ Colour
Monitor. Operating system : Windows 7
Mouse : Optical Mouse. Ultimate
Ram : 512 Mb.

Coding Language : Python


Methodology

Feature Extraction and Comparison


Image Acquisition

Preprocessing

Feature Extraction

Feature Comparison
Methodology

Machine Learning Classification


Image Acquisition

Preprocessing

Feature Extraction

Model Training
Methodology
Deep Learning-Based
Approach
Image Acquisition

Data Augmentation

Model Design

raining and Validation

Testing and Deployment


Methodology
Hybrid Approach Combining Image Processing
and AI
Image Acquisition

Preprocessing and Initial Detection

Feature Extraction Using Image Processing

Advanced Classification Using AI

:Ensemble Decision Making


Result
Result
Conclusion
This paper presents a fake currency detection model
for Indian 500 and 2000 rupee notes, using the
OpenCV library in Python3. It analyzes 10 features
with three algorithms. Users input images through a
Tkinter-based GUI, which also shows detailed feature
analysis. The model processes images in about 5
seconds, achieving 79% accuracy for genuine notes
and 83% for counterfeit notes.
Future Scope

Expansion to Multiple Denominations and Currencies

Integration with Real-Time Systems

Improved Accuracy with Advanced Algorithms

Enhanced Feature Extraction Techniques


Thank
You

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy