End of the project is the technology of currency recognition basically AIMS for identifying and extracting visible and invisible features of currency notes and till now many techniques have been proposed stering for the fake currency note but the best way to use the visible features of the note or colour and size
The scope of work and idea is this project proposes and approach the 12 detect a currency note be in circular in our country by using their image our project will provide required mobility and compatibility to most of the people and provides a credible accuracy for the fake currency detection we are using machine learning to make it portable and efficient.
The overview of the project is the fake currency detection using machine learning was implemented on matlab features of currency note like serial number security thread identification mark Mahatma Gandhi portrayed what extracted the process star and from image acquisition to calculation of intensity of each extracted feature.
The application the applications are fake currency detection system can be utilised in shops Bank counters and end computerised tailor machine and auto merchant machines and so on the systems are created utilizing diverse techniques and
The future scope of this project is many different adaptation test and innovations have been kept for the future due to lack of time as which a work concerns de per analysis of particular mechanisms new proposal Pride different methods or simply curiosity in future we will be including ammonia for currency conversion and we can implement the system for foreign currencies and tracking of device location through which the currency scan and maintain the same in the database.
Project on fake currency recognition using image processing ppt final (3).pptx
1. Project On
Recognition of fake currency using image processing
Presented by : Under the guidance of
B.Anivinder Reddy - 18001A0403 Sri . M. Sreedhar
M.K.Harika - 18001A0410 Assistant Professor Adhoc
B.V.Sumathi - 19005A0403 Department of ECE
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY
ANANTAPUR
ANANTAPURAMU – 515002, AP, INDIA
2. Contents:
1.Aim of The Project
2.Introduction
3.Scope of Work and Idea
4.Overview of The Project
5.Flow chart
6.Steps involved
7.Features involved
8.Block diagram
9.Results
10.Novelty of project
11.Advantages
12.Limitations
13.Applications
14.Conclusions
15.Future scope
16.References
3. Aim of the project:
The technology of currency recognition basically aims for identifying and extracting visible
and invisible features of currency notes. Until now, many techniques have been proposed to
identify the currency note. But the best way is to use the visible features of the note for
example, color and size.
4. Introduction:
Fake Currency Note is a term that refers to the counterfeit currency notes that rapidly
circulated in the economy . These days technology is been growing very fast. Consequently
the banking sector is also getting modern day by day. Currency duplication also known as
counterfeit currency is a vulnerable threat on economy.
In the proposed model , acquired image of currency note is checked whether it is fake or
real on the basis of counting the number of interruptions in the security thread. The camera
pictures are noted and analysed by MATLAB program installed on computer.
5. Problem statement:
The counterfeiters nowadays, can evade the chemical property & physical feature based
counterfeit paper currency detection system due to technological advancement.
The circulation of a large amount of fake currency increases the amount of money in
circulation, which may lead to high demand for goods and commodities. The rise in
demand in turn creates a scarcity of goods, leading to a rise in the price of the goods. This
leads to currency devaluation
6. Scope of work and idea:
This project proposes an approach that will detect fake currency note being circulated in
our country by using their image. Our project will provide required mobility and
compatibility to most of the people and provides credible accuracy for the fake currency
detection. We are using machine learning to make it portable and efficient.
7. Overview of the project:
The fake currency detection using machine learning was implemented on MATLAB.
Features of currency note like serial number, security thread, Identification mark, Mahatma
Gandhi portrait were extracted. The process starts from image acquisition to calculation of
intensity of each extracted feature.
9. Steps involved :
Image Acquisition : It is the action of retrieving an image from source. It goes through the image which is
given as a path as a input. It also checks the over all image which is given as input. It selects the required
features to proceed for the further processing.
Pre Processing : Pre-processing is a familiar name for operations with images at the lowest level of
abstraction -- both input and output are intensity images. The aim of Pre-processing is an improvement of
the image data that suppresses unwanted distortions or enhances some image features essential for further
processing.
Initial Segmentation : In this step we divide an image into various parts that have similar attributes which
are called as image objects. It is the first step for image analysis
10. Continuation..
Post Processing : Adjusting exposure, contrast and brightness and also adjusting colors, hues, tones,
saturation and light levels. It also checks the true and fake pixels of the image.
Gray Scale Conversion : This step is used to enhance the gray image to emphasize dark lines in lighter
background and also helps in checking the black strips of the real note . It also detects exact features of
the note after converting the image into gray scaling.
Feature Extraction : Extracts the features that are needed to be compared and to conclude whether the
note is fake or real . In the over all processing each step is having the unique way of extracting the
features of the real and fake note.
11. Features involved:
Contrast : The difference in brightness between light and dark areas of image. Contrast determines the
number of shades in the image.
Energy : It is the distances of some quality between the pixels of some locality
Homogeneity : It expresses how similar certain elements(pixels) of the image are. Generally an image is
homogenous if each pixel in the image has the same color .
Mean : Mean value is the sum of pixel values divided by the total number of pixel values.
Entropy : Entropy is a measure of image information content, which is interpreted as the average
uncertainity of information source. It is defined as corresponding states of intensity level which individual
pixels can adapt.
12. Continuation:
RMS : To get an estimate of the similarity between source image and the segmented image, we use root
mean square error. Using this the data can be divided by best fit to find out how concentrated an image is.
Standard deviation : Standard deviation of the image implies a gross measure of the imprecision or
variation about the target value of light intensity at each such data point
Variance : The variance gives an idea how the pixel values are spread.
Smoothness: Smoothness measures the relative smoothness of intensity in a region. It is high for a region of
constant intensity and low for regions with large excursions in the values of its intensity levels.
IDM : Inverse Difference Moment is usually called homogeneity that measures the local homogeneity of an
image
14. Technique used:
Support Vector Machine
Support Vector Machine or SVM is one of the most popular Supervised Learning algorithms,
which is used for Classification as well as Regression problems.
Support vector machines (SVMs) are a set of supervised learning methods used
for classification, regression and outliers detection.
The advantages of support vector machines are: Effective in high dimensional spaces. Still
effective in cases where number of dimensions is greater than the number of samples.
17. Novelty of project:
Detection of the fake currency note is done by counting the number of interruptions in the
thread line.
Predicts whether the note is real or fake on the basis of number of interruptions.
If the number of interruption is zero, then it is real note otherwise it is fake note. And also
we calculate the entropy of the currency notes for the efficient detection of fake
currency note.
MATLAB software is used to detect the fake currency note.
20. Applications:
Fake currency detection system can be utilized in shops, bank counters and in computerized
teller machine, auto merchant machines and so on.
The systems are created utilizing diverse techniques and algorithms.
21. Conclusion :
The survival of the financial symmetry may be affected with its value, rapidity, output and wellbeing by
counterfeiting of bank notes.
With improvement of recent banking services, automatic methods for paper currency recognition
become vital in many applications such as in ATM and automatic goods seller machines.
The system has a best performance for both agreeing valid banknotes and deleting invalid data. It also
shows the techniques for currency recognition using image processing.
The Indian currency notes have been identified and counterfeit notes has been found. This work is done
by using various filters. This method is very easy to implement in real time world. At last we have
concluded that if we propose some efficient preprocessing and feature extraction method then we can
improve the accuracy of identification system. We can also develop app for detection of fake currency.
22. Future scope:
Many different adaptations, tests and innovations have been kept for the future due
to the lack of time. As future work concerns deeper analysis of particular mechanisms, new
proposals to try different methods or simple curiosity.
1. In future we would be including a module for currency conversion.
2. We can implement the system for foreign currencies.
3. Tracking of device’s location through which the currency is scanned and maintaining the
same in the database.
23. References :
Megha Thakur and Amrit Kaur, "Various Fake Currency Detection Techniques", International Journal For
Technological Research In Engineering, vol. 1, no. 11, July 2014.
B R Kavya and B Devendran , "INDIAN CURRENCY DETECTION AND DENOMINATION USING
SIFT", International Journal of Science Engineering and Technology Research, vol. 4, no. 6, June 2015.
W. K. El Said, "Fake Egyptian Currency Detection System using Texture and Shape
Characteristics", International Journal of Computer Applications (0975 – 8887), vol. 143, no. 2, June
2016.
Binod Prasad yadav,C.S patil,R.R Karhe,P.H patil – ” HSV Technique by using MATLAB “The fake
currency is detected manually.