IJARR, 5(9), 2019; 86-92

International Journal of Advanced Research and Review

FAKE CURRENCY DETECTION WITH MACHINE LEARNING

Manjunatha K H , Kiran P V , Usha. G

Asst. Professor, Asst. Professor, Asst. Professor

ABSTRACT
The topic of determining if a particular sample of cash is counterfeit is addressed in this article. The
indicated colours, width, and serial numbers are only a few of the classic techniques and approaches
that may be used to identify counterfeit cash. Image processing has led to the proposal of several
machine learning algorithms that provide 99.9 percent accuracy for the counterfeit cash in this era of
improved computer science and high computational approaches. Colour, form, paper width, and
picture filtering on the note are entities that may be detected and recognised using algorithms. This
study presents a technique for detecting counterfeit money by using K-Nearest Neighbours in
conjunction with image processing. The computer vision job is well-suited to KNN because of its
excellent accuracy for tiny data sets. To ensure accurate data and information about the entities and
properties associated with money, a banknote authentication dataset has been developed using
advanced computational and mathematical techniques. In order to achieve the desired outcome with
precision, data processing and extraction make use of machine learning algorithms in conjunction with
image processing.
INTRODUCTION
In this century where the majority of people are aware of technology and how it works,
many of them indulge in unlawful activities. One of such activities is the production of fake currency
which is practiced to deceive people. In this proposal, it is focused on this illegitimate practice and try

86
 IJARR, 5(9), 2019; 86-92
to bring forward a solution for it. According to a survey, the maximum number of cases of counterfeit
in India still relate to fake currency, There were 132 cases of counterfeit currency in 2018, which shot
up 37 percent to 181 in 2019[7]. In Order to stop this fraudulent activity, a system is proposed that can
be integrated into electronic devices that will detect the fake note as soon as it is scanned by the device.
Some of the techniques which are considered are used previously and include KNN which will be
utilized in the proposed system with enhanced accuracy. K-nearest neighbors (KNN) is an algorithm
that stores all the available data and classifies a new data point based on the similarity. This means
when new data appears then it can be easily classified into a good suite category by using the KNN
algorithm [6]. Usually, the Euclidean distance is used as the distance metric. Then, it assigns the point
to the class among its k nearest neighbors (where k is an integer).
LITERATURE REVIEW
“Accelerating business growth with big data and artificial intelligence,” Artificial Intelligence
(AI) is considered to be the fourth industrial revolution. Artificial Intelligence with the help of big data
has transformed all industries around the world Artificial intelligence refers to the simulation of human
or animal intelligence in computational systems so that they are programmed to think like Intelligent
beings and mimic the actions of intelligent entities. Computational systems which have programmed
intelligence can solve different real-world problems far more accurately and efficiently than
computational systems that are deterministic and hardcoded. Since many problems in business and
business analytics cannot be solved by deterministic systems, AI plays a major role in tackling
problems in the business world Machine learning and deep learning which are subsets of the field of
AI is widely used to solve and optimize many problems in business such as marketing, credit card
fraud detection, algorithmic trading, customer service, portfolio management, product
recommendation according to the needs of customers, insurance underwriting. AI and big data have
revolutionized the business world and this paper discusses some AI and big data technologies that are
currently being used to accelerate business growth.
“Oversampling based Classifiers for Categorization of Radar Returns from the Ionosphere,”
The process of manually checking, validating, and excluding data in an ionospheric verylow-
frequency (VLF) analysis during extreme events is a labor-intensive and time-consuming task.
However, this task can be automated through the utilization of machine learning (ML) classification
techniques. This research paper employed the Random Forest (RF) classification algorithm to
automatically classify the impact of solar flares on ionospheric VLF data and erroneous data points,
such as instrumentation errors and noisy data. The data used for analysis were collected during
September and October 2011, encompassing solar flare classes ranging from C2.5 to X2.1. The F1-
87
 IJARR, 5(9), 2019; 86-92
score values obtained from the test dataset displayed values of 0.848; meanwhile, a more detailed
analysis revealed that, due to the imbalanced distribution of the target class, the per-class F1-score
indicated higher values for the normal data point class (0.69–0.97) compared to those of the anomalous
data point class (0.31 to 0.71). Instances of successful and inadequate categorization were analyzed
and presented visually. This research investigated the potential application of ML techniques in the
automated identification and classification of erroneous VLF amplitude data points; however, the
findings of this research hold promise for the detection of short-term ionospheric responses to, e.g.,
gamma ray bursts (GRBs), or in the analysis of pre-earthquake ionospheric anomalies.

“Automatic Indian New Fake Currency Detection Technique,” In India,’ currency’ is the means
of Transaction so there is more value for currency in our social and economic development. Here,
currency exists in the form of coins, banknotes and electronic data. Fake money or counterfeit notes
is the dangerous or acute problem in front of whole world, and India is also a part of this fake currency.
Modernization in the financial system is a milestone in protecting the economic development and now
a days Indian government has become conscious about this so demonetization of Rs 1000 and Rs 500
notes is the latest example of it. But again we have Rs 2000 as a new currency in market. so as the
highest value note there is a chance that corrupt people will try to make it as a counterfeit. So main
objective of this paper is to study different key features of new genuine currency and use such
techniques to detect and verify new currency circulated by Reserve Bank Of India. There are Different
techniques which are used to distinguish between counterfeit notes and genuine one. By using different
components of Digital Image processing such as image processing, image segmentation,
characteristics extraction, comparing images etc. we can extract the features of genuine notes. It is a
very challenging task for detecting fake currency.
“Fake currency detection using image processing, The advancement of color printing technology
has increased the rate of fake currency note printing and duplicating the notes on a very large scale.
Few years back, the printing could be done in a print house, but now anyone can print a currency note
with maximum accuracy using a simple laser printer. As a result the issue of fake notes instead of the
genuine ones has been increased very largely. India has been unfortunately cursed with the problems
like corruption and black money .And counterfeit of currency notes is also a big problem to it. This
leads to design of a system that detects the fake currency note in a less time and in a more efficient
manner. The proposed system gives an approach to verify the Indian currency notes. Verification of
currency note is done by the concepts of image processing. This article describes extraction of various
features of Indian currency notes. MATLAB software is used to extract the features of the note. The

88
 IJARR, 5(9), 2019; 86-92
proposed system has got advantages like simplicity and high performance speed. The result will
predict whether the currency note is fake or not.
“A Review on Fake Currency Detection using Image Processing,” Fake Indian Currency Note
(FICN) is a term used by officials and media to refer to counterfeit currency notes circulated in
theIndian economy. However several central and state agencies are working together and the Ministry
of Home Affairs hasconstituted the Fake Indian Currency Notes Co-ordination Centre (FCORD) to
curb this menace. We propose a new approachto detect fake Indian notes using mobile camera and
Image processing. We will convert Indian currency into more the 150+different currencies values to
help tourist all over the world. In this project we match features between two images usingBrute-Force
Matching with ORB Descriptors. After applying BFMatcher with ORB we get Matcher Object and by
usingknnMatch we get the list of best k matches depending upon the value of K. currency duplication
also known as counterfeit currency is a vulnerable threat on economy. Although fake currency isbeing
printed with precision, the Crime Investigation Department (CID) says that they can be detected with
some effort.Currency printed by local racketeers can be detected easily as they use the photographic
method, hand engraved blocks,lithographic processes and computer colour scanning. In counterfeit
notes, the watermark is made by using opaque ink,painting with white solution, stamping with a dye
engraved with the picture of Mahatma Gandhi. Tourists are the mostvulnerable people to fake
currencies, because they don't know the proper and precise way of finding the differencebetween fake
and real currencies note. So automatic identification of currencies using image processing technique
will behelpful to these peoples.it is also be useful at other workplaces. . The system designed to check
the Indian currency notewith denominations 10, 20, 50, 100, 200, 500 and 2000. It will pre-process
the digital pictures and organise the preparedarrangement of information and it will distinguish in
monetary forms. This paper proposes a convenient and cheapestmethod for identifying Indian
currencies. At the end of the process user can know whether the currency note is fake or realand it's
equivalent currency value into more then 150 counties
“Fake Currency Detection,” Great technological advancement in printing and scanning industry
made counterfeiting problem to grow more vigorously. As a result, counterfeit currency affects the
economy and reduces the value of original money. Thus it is most needed to detect the fake currency.
Most of the former methods are based on hardware and image processing techniques. Finding
counterfeit currencies with these methods is less efficient and time consuming. To overcome the above
problem, we have proposed the detection of counterfeit currency using a deep convolution neural
network. Our work identifies the fake currency by examining the currency images. The transfer learned
convolutional neural network is trained with two thousand currency note data sets to learn the feature

89
 IJARR, 5(9), 2019; 86-92
map of the currencies. Once the feature map is learnt the network is ready for identifying the fake
currency in real time. The proposed approach efficiently identifies the forgery currencies of 2000 with
less time consumption.
“Automatic Cash Deposite Machine With Currency Detection Using Fluorescent And UV
Light,” Authentication is an important part of any secrete operation and concept is applicable for
trustworthy Automatic Teller Machine which ensures that, only individuals with corroborated
identities can log on to the system or access system resources. In this paper, I survey the literature to
describe the ways that ATMs have influenced these aspects of security, and conclude with suggestions
for further research. ATM system follows four digit PIN authentication process for user validation.
Many researchers suggest the additional authentication process such as biometric, thumb and face
validation. Now a days we are aware of the ATM which make the task of money withdraw more
flexible. In addition to this banks are introducing Cash deposit machine (CDM) that makes easy to
deposit cash to user account. As day by day this process is becoming easier, hackers started their job
to disturb the ATM process. This paper describes basic ATM attacks.
“A Review on Fake currency detection using feature extraction,” Fake currency identification is
a serious problem all around the world, affecting the economies of almost every country, including
the United States. India. The prospective agreements are to make use of either the currency's synthetic
qualities or Make use of its physical look. The procedure The information presented in this study is
dependent on physical conditions. The appearance of the Indian currency It has been received that
calculations are being prepared. remove the highlights, such as security string, intaglio printing (RBI
logo) and distinctive characteristics proof imprints, which have come to be accepted as Indian currency
security highlights To accomplish this, system that is becoming increasingly strong and precise, the
All three highlights have received a conclusive score. Intertwined to distinguish between authentic
and fake monetary benchmarks The finding of counterfeit money The suggested system has an
accuracy of one hundred percent. Another utilised parameter The mean square blunder, which is
around 1%, is used to quantify the presentation of the proposed system. It may be accepted by ordinary
persons as well, who are frequently faced with the problem of distinguishing between genuine and
counterfeit monetary standards.
CONCLUSION AND FUTURE WORK
After running the algorithms and looking at the data, we can say that all three of them did a fantastic
job of identifying fake and real notes in the dataset. As we saw in the last part, KNN, however, fared
better than the other two. With just two false positives, it achieved a 99.9 percent accuracy rate in
detecting counterfeit currency. The data set was little, thus this finding is constrained. Its present
90
 IJARR, 5(9), 2019; 86-92
performance may not hold up in a real-world setting due to its small sample size (1372 samples). Using
this as a foundation, we suggest compiling a much bigger dataset with realistic images of actual and
counterfeit banknotes. The resulting model will be much more accurate thanks to this. In addition,
highly accurate deep learning techniques for image processing, such as Convolutional Neural
Networks (CNNs), may be used with a big data collection. In addition, the project may skip the wavelet
processing and go straight to picture analysis using CNN. The system may become more handy and
easy to use as a result of this. In addition, with the aid of CNN, consumers will be able to instantly
click on an image and have it validated, which is advantageous for financial institutions. Therefore,
the aforementioned steps may be accomplished to enhance the project's strength and professionalism
[10].
REFERENCES
[1] D. V. Kapare, S. Lokhande, and S. Kale, “Automatic Cash Deposite Machine With Currency Detection
Using Fluorescent And UV Light,” vol. 3, pp. 309–311, 2013.

[2] M. N. Rathore and J. Sagar, “A Review on Fake currency detection using feature extraction,” vol. 10, no.
11, pp. 407–411, 2019.

[3] K. Santhanam, S. Sekaran, S. Vaikundam, and A. M. Kumarasamy, “Counterfeit currency detection

[4] P. Ponishjino, K. Antony, S. Kumar, and S. Jebakumar, “Bogus currency authorization using HSV
techniques,” Proc. Int. Conf. Electron. Commun. Aerosp. Technol. ICECA 2017, vol. 2017- January, pp. 179–
183, 2017, doi: 10.1109/ICECA.2017.8203667.

[5] Q. Zhang and W. Q. Yan, “Currency Detection and Recognition Based on Deep Learning,” Proc. AVSS
2018 - 2018 15th IEEE Int. Conf. Adv. Video Signal Based Surveill., pp. 0–5, 2019, doi:
10.1109/AVSS.2018.8639124.

[6] A. Upadhyaya, V. Shokeen, and G. Srivastava, “Analysis of counterfeit currency detection techniques for
classification model,” 2018 4th Int. Conf. Comput. Commun. Autom. ICCCA 2018, pp. 1–6, 2018, doi:
10.1109/CCAA.2018.8777704.

[7] S. Arya and M. Sasikumar, “Fake Currency Detection,” 2019 Int. Conf. Recent Adv. Energy Efficient
Comput. Commun. ICRAECC 2019, pp. 2019–2022, 2019, doi: 10.1109/ICRAECC43874.2019.8994968.

91
 IJARR, 5(9), 2019; 86-92

[8] A. Kumar and A. Kumar, “Dog Breed Classifier for Facial Recognition using Convolutional Neural
Networks,” pp. 508–513, 2020.

[9] M. Haider Ali, “Thesis Report on Fake Currency Detection using Image Processing Method,” Akiful
Mohaimin Rifat Islam Shahriar Chowdhury, no. 13301148, pp. 1–38, 1330.

[10] M. N. Shende and P. P. Patil, “A Review on Fake Currency Detection using Image Processing,” Int. J.
Futur. Revolut. Comput. Sci. Commun. Eng., vol. 4, no. 1, pp. 391–393, 2018.

[11] Reddy, Kallem Niranjan, and Pappu Venkata Yasoda Jayasree. "Low Power Strain and Dimension Aware
SRAM Cell Design Using a New Tunnel FET and Domino Independent Logic." International Journal of
Intelligent Engineering & Systems 11, no. 4 (2018).
[12] Reddy, K. Niranjan, and P. V. Y. Jayasree. "Design of a Dual Doping Less Double Gate Tfet and Its
Material Optimization Analysis on a 6t Sram Cells."
[13] Reddy, K. Niranjan, and P. V. Y. Jayasree. "Low power process, voltage, and temperature (PVT) variations
aware improved tunnel FET on 6T SRAM cells." Sustainable Computing: Informatics and Systems 21 (2019):
143-153.
[14] Reddy, K. Niranjan, and P. V. Y. Jayasree. "Survey on improvement of PVT aware variations in tunnel
FET on SRAM cells." In 2017 International Conference on Current Trends in Computer, Electrical, Electronics
and Communication (CTCEEC), pp. 703-705. IEEE, 2017
[15] Karne, R. K. ., & Sreeja, T. K. . (2023). PMLC- Predictions of Mobility and Transmission in a Lane-Based
Cluster VANET Validated on Machine Learning. International Journal on Recent and Innovation Trends in
Computing and Communication, 11(5s), 477–483. https://doi.org/10.17762/ijritcc.v11i5s.7109
[16] Radha Krishna Karne and Dr. T. K. Sreeja (2022), A Novel Approach for Dynamic Stable Clustering in
VANET Using Deep Learning (LSTM) Model. IJEER 10(4), 1092-1098. DOI: 10.37391/IJEER.100454.

92