Counterfeit it is easily possible for a person

notes are one of the biggest problem occurring in cash transactions. For
country like India, it is becoming big hurdle; because of the advances in
printing, scanning technologies it is easily possible for a person to print
fake notes with use of latest hardware tools. Detecting fake notes manually
becomes time-consuming and untidy process hence there is need of automation
techniques with which currency recognition process can be efficiently done.
This paper is a based on the work which gives solution for fake currency
problem. The approach consists of a number of components including image
processing, edge detection, image segmentation, feature extraction, comparing
images. It becomes very important to select the right features and proper
algorithm for this purpose. The basic requirements for an algorithm to be
considered as practically implementable are simplicity, less complexity, high
speed and efficiency. The main aim is to design an easy but efficient algorithm
that would be useful for maximum number of currencies, because all currencies
have different security features, making it a tough job to design one algorithm
that could be used for recognition of all available currencies. The image
processing approach is discussed with MATLAB to detect the features of paper
currency which involves changing the nature of an image in order to improve its
pictorial information for human interpretation. The result will be whether
currency is genuine or counterfeit.


Keywords: Counterfeit, feature extraction, image processing, MATLAB.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now



1. Introduction

As this is the age of automation, almost every task in
industries has been automated. Now-a-days there are many things where
automation has brought radical changes. Therefore Automatic methods for bank
note recognition are required in many applications such as automatic
selling-goods and vending machines. Extracting sufficient monetary
characteristics from the currency image is essential for accuracy and
robustness of the automated system. This is a challenging issue to system


Every year RBI (Reserve bank of India) face the
counterfeit currency notes or destroyed notes. Handling of large volume of
counterfeit notes imposes additional problems. Therefore, involving machines (independently
or as assistance to the human experts) makes notes recognition process simpler
and efficient. The only solution that is presently available for common man to
detect counterfeit currency is Fake Note Detector Machine. This machine is
mostly available only in banks which is not reachable every time by average
citizen. All these scenarios need a kind of solution for common people to judge
a forged bank note and to refrain our currency from losing its value.


Recognition of counterfeit currency means detection of
fake currency from the genuine ones. The methodology of this project will be
extracting unique features of the Indian currency note through image processing


Digital Image Processing is a rapidly evolving field
with growing applications in Science and Engineering. It encompasses the
processes whose inputs and outputs are images and extract attributes from
images including the recognition of individual objects. MATLAB is a high
performance language for technical computing. It integrates computation,
visualization and programming in an easy to use environment.


Feature extraction is a type of dimensionality
reduction that efficiently represents interesting parts of an image as a
compact feature vector. This approach is very useful when image sizes are large
and reduced feature representation is required to quickly completer tasks such
as image matching and retrieval. This overture contains a large number of steps
including image acquisition, gray scale conversion, edge detection, image
segmentation, feature extraction and comparison of images.


Image acquisition is the
creation of digital images, typically from a physical scene. In the proposed
work, the image will be acquired by using scanner.The image is then stored in
the computer for further processing. Edge detection and image segmentation are
the most important tasks performed on the images.


1.1 Edge detection


Edge detection is an image processing technique for finding the boundaries
of objects within images. It works by detecting discontinuities in brightness.
It is used for image segmentation and data extraction.
Edge detection is one of the fundamental steps in image processing, image
analysis, image pattern recognition, and computer vision techniques.


1.2 Image Segmentation


Image segmentation
is the process of dividing an image into multiple parts. This is typically used
to identify objects or other relevant information in digital images. An effective approach to performing image
segmentation includes using algorithms, tools, and a comprehensive environment
for data analysis, visualization, and algorithm development. Segmentation algorithms
generally are based on one of two basic properties of intensity values-




This approach is to partition an
image based on abrupt changes in
intensity such as edges in an image.




This approach is to partition am image into regions
that are similar according to a set of predefined area.


2. Related Work

     From the
literature, it is revealed that many researchers have done work on the
identification of fake currency. Let us explain some of the important references.
Recently in 2017, identification of newly launched 500 and 2000 notes in the
Indian market has been performed 1. A UML activity model is designed to
represent the dynamic aspects for identification of fake currency and
successfully implemented on newly launched a note of Rs 2000 by an Indian


Another research work conducted a survey 2 by going
through different literature, which describes different techniques of fake note
identification. This is a MATLAB based system for automatic recognition of
security features of Indian currency.


Another study describes an approach in which six
characteristics of Indian paper currency are selected for counterfeit detection
included identification mark, security thread, watermark, numeral watermark, floral
design and micro-lettering 3. The characteristic extraction is performed on
the image of the currency and it is compared with the characteristics of the
genuine currency. The decision making is done by calculating the black pixels.
This article is aimed to design a low cost system and quick decision making


study focuses on
reading mechanism of Indian currency note number recognition using image
processing for the existing ATM machines 4. The algorithm developed is tested
for 1000 rupee notes which provides an accuracy of 86% for serial number
extraction of Indian rupee currency note number and takes 0.568079 seconds for
its execution.


A new technique is proposed 5 in which images of the paper currency will
be acquired through camera by applying UV (ultra violet) backlighting, extra
light to the banknote so that the hidden marks of currency are appeared on the
image. Then image will be further processed by applying the image processing
techniques using LABVIEW tool. Morphological image processing based feature
extraction for Indian currency recognition and verification has been done 6.


3. Proposed Work

     The proposed system will work on 2000
rupee denomination. The base color
of the note is magenta. The note has other designs, geometric patterns aligning
with the overall color scheme, both on the obverse and the reverse. The size of
the new note is 66mm x 166mm. The system has two images, one is original
image of the paper currency and other is the test image on which recognition is
to be performed. 


proposed algorithm for the discussed paper currency recognition system is
presented as follows- 


Image of paper currency will be acquired by simple scanner.

The image acquired is RGB image and then it will be converted into gray scale.

Edge detection of the whole gray scale image will be performed.

After detecting edges, the four features of the paper currency will be cropped
and segmented.

After segmentation, the features of the paper currency will be extracted.

The characteristics of test image are compared with the original pre-stored
image in the system.

If it matches then the currency is genuine otherwise counterfeit.


the proposed method features of paper currencies are employed that are used by
people for differentiating different banknote denominations. Basically, at
first instance, people may not pay attention to the details and exact features
of banknotes for their recognition, rather they consider the common features of
banknotes such as the size, the background color (the basic color), and texture
present on the banknotes. In this method, these characteristics will be used to
differentiate between different banknote denominations-



Latent image with denominational numeral 2000 can be seen when
the banknote is held at 45 degree angle at eye level.



This feature is exclusive for 2000 rupee note and appears between
the vertical band and Mahatma Gandhi portrait. It contains the word ‘RBI’ and ‘2000’.
This feature can be seen well under a magnifying glass.


Identification Mark

A symbol with intaglio prints which can be felt by touch, helps
the visually impaired to identify the denomination. In 2000 denominations the
identification mark is a rectangle with Rs 2000 in raised print on the right.


The below diagram shows the step-by step process of this currency
recognition system-




















Figure.1 Design Flow of Indian Paper Currency Recognition


5. Conclusion

     This paper discussed a technique for
recognition of paper currency of India. The technique uses four characteristics
of paper currency including identification mark, security thread, latent image
and watermark. The system may extract the hidden features i.e. latent image and
watermark of the paper currency. The proposed work is an effort to suggest an
approach for the feature extraction of Indian paper currency. Approach
suggested from the beginning of image acquisition to converting it to gray
scale image and up to the word segmentation has been stated. The work will
surely very useful for minimizing the counterfeit currency.