IJSTE - International Journal of Science Technology & Engineering | Volume 2 | Issue 12 | June 2016

ISSN (online): 2349-784X

Identification of Paper Currency Techniques: A

Survey
Snehlata Sahu
RCET, Bhilai (C.G.)

Toran Verma
RCET, Bhilai (C.G.)

Abstract
Paper currency identification is an image processing technique i.e. worn to recognize currency of different countries. The paper
currencies of different countries are possibly interweaved collectively consequently rises ever more. It is a challenge for standard
currency recognition systems. However, the main focus of most of the standard currency recognition systems and machines is on
recognizing forged currencies. Hence there is very vital role of currency identification system and it is essential that the
identification system should be very accurate. A thriving approach for paper currency identification depends upon preprocessing, feature extraction and classification of that currency image. In this paper, we have gone through different literature
which describes different techniques of paper currency recognition. Finally we have concluded that if we apply some efficient
pre-processing and feature extraction technique than we can improve the accuracy of identification system.
Keywords: Image Processing, Binarisation, Heuristic Analysis, Morphology Filtering, Feature Extraction
________________________________________________________________________________________________________
I.

INTRODUCTION

Innovation of the monetary system is a milestone in defensive the economic affluence, and maintaining social agreement. There
are just about more than 140 currencies all over the world, apiece of them looking totally diverse. Automatic machines
competent of recognizing banknotes are extremely used in automatic dispensers of a number of unlike products, ranging from
cigarettes to bus fare tickets, as well as in lots of automatic banking operations. By development of present banking services,
automatic schemes for paper banknote identification are noteworthy in numerous applications. The necessities for an automatic
currency identification system have presented many researchers to make robust and trustworthy techniques. Rapidity and
accuracy of processing are two imperative factors in such systems. The technology of currency identification aims to investigate
and take out the hidden and visible inscription on banknote for efficient classification. The following figure shows the different
features of Indian currency.

Fig. 1: Features of Indian currency note

The existing paper money recognition ways, within the current literature, involve extraction of options for paper currency
classification. Paper money recognition systems ought to be clever to acknowledge banknotes from both sides and every
direction. Since banknotes are also faulty throughout circulation, the designed system ought to have a crucial exactness in police
investigation torn or worn banknotes. The best means is to form use of the visible options of the paper money, for instance, the
dimensions and color of the paper money [1]. However, this sort of ways has nice limitations as banknotes have gotten worn and
torn with the passing of your time and that they area unit even dirtier once holding by dirty hands or in dirt. If any paper currency
is dirty or might its going to it should be become the other color then the color content of paper currency may amendment for the
most part. Varied authors have worked for paper money recognition. Until now, there are a unit several ways planned for paper
money recognition.
Further in this paper in Section II we have gone through different literature, in section III

All rights reserved by www.ijste.org

607

Identification of Paper Currency Techniques: A Survey

(IJSTE/ Volume 2 / Issue 12 / 109)

II. LITERATURE SURVEY

Automatic substantiation of banknote is flattering a gradually more urgent problem because of new and improved uses of
counterfeits. Henceforth we have gone through some literatures.
YingLi Tian et. Al. developed a novel camera-based computer vision technology to automatically recognize banknotes for
assisting visually impaired people. Our banknote recognition system is robust and effective with the following features: 1) high
accuracy: high true recognition rate and low false recognition rate, 2) robustness: handles a variety of currency designs and bills
in various conditions, 3) high efficiency: recognizes banknotes quickly, and 4) ease of use: helps blind users to aim the target for
image capture. To make the system robust to a variety of conditions including occlusion, rotation, scaling, cluttered background,
illumination change, viewpoint variation, and worn or wrinkled bills, we propose a component-based framework by using
Speeded Up Robust Features (SURF). Furthermore, we employ the spatial relationship of matched SURF features to detect if
there is a bill in the camera view. This process largely alleviates false recognition and can guide the user to correctly aim at the
bill to be recognized. The robustness and generalizability of the proposed system is evaluated on a dataset including both positive
images (with U.S. banknotes) and negative images (no U.S. banknotes) collected under a variety of conditions. The proposed
algorithm, achieves 100% true recognition rate and 0% false recognition rate. Our banknote recognition system is also tested by
blind users [IEEE 2014] [1].
Ankush Roy et. al. describes a system developed for discriminating fake notes from genuine ones and apply it to Indian
banknotes. Image processing and pattern recognition techniques are used to design the overall approach. The ability of the
embedded security aspects is thoroughly analyzed for detecting fake currencies. Real samples are used in the experiments that
show a high-precision machine can be developed for authentication of paper money. The system performance is reported for
both accuracy and processing speed. The analysis of security features to prevent counterfeiting highlights some of the issues that
should be considered in designing of currency notes in the future [Springer 2015] [2].
Yifeng Liu et. al. said that Haar wavelet is the simplest possible wavelet, and Support Vector Machine (SVM) is an effective
classifier. This paper proposes a new method that combines the Haar wavelet and SVM for the first time to solve the problem of
small denomination banknotes recognition with small computations, real timing and excellent performance. The key idea of this
method is to extract the waveform features and transform them to the digitalize support vectors with fixed length. We illustrate
our method on a dataset that comprises 220,000 samples of 2,200 different banknotes, and the approach achieves an average
recognition rate of 99.9877%. The experimental results show our method is also simple, fast and robust. Our method has been
applied in JBYD-8801A RMB-banknote counter [JOICS 2014] [3].
Binod Prasad Yadav et. al. said that Counterfeit 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. Many
techniques have been proposed with the use of MATLAB, feature extraction with HSV color space and other applications of
image processing. We have implemented a fake note detection unit with MATLAB algorithm. This paper is a based on the same
project to give solution for fake currency problem [IJESIT 2014] [4].
Allah Bux Sargano et. al. said that Intelligent systems on Paper currency recognition and verification are inevitable for modern
banking services. These systems are used in Auto-seller machines, vending machines etc. Extracting sufficient and reliable
monetary characteristics are essential for accuracy and performance of such systems. This paper proposes a new intelligent
system for paper currency recognition. Pakistani paper currency has been considered, as a case study, for intelligent recognition.
This paper identifies, introduces, and extracts robust features from Pakistani banknotes. After extracting these features, the paper
proposes to use three layers feed-forward Backpropagation Neural Network (BPN) for intelligent classification. The proposed
technique and system are simple and comparatively less time consuming which makes it suitable for real-time applications. In
order to evaluate the performance of the proposed technique, experiments have been conducted on 175 Pakistani banknotes. The
results indicate that system has 100% recognition ability on properly captured images [JIFS 2014] [15].
III. STEPS FOR CURRENCY IDENTIFICATION SYSTEM
There are different processing steps for analysis of paper currency identification is pre-processing, morphological filtering,
binarization, heuristic analysis, segmentation and feature extraction etc. The block diagram for this approach is shown in fig.2
given below:

All rights reserved by www.ijste.org

608

Identification of Paper Currency Techniques: A Survey

(IJSTE/ Volume 2 / Issue 12 / 109)

Fig. 2: Steps for Currency Recognition

Image Pre-processing:
In order to feature extraction of paper currencies effectively, the currency pictures square measure collected with applicable
abstraction resolutions and brightness resolution, wherever the abstraction resolution describes what percentage pixels comprise
a digital image or what percentage dots square measure in every in. of a digital image. The construct of the brightness resolution
addresses however accurately the digital pixels brightness will represent the intensity of the initial image. when document
scanning (see fig.2), a sequence of information pre-processing operations square measure ordinarily applied to the photographs
of the documents so as to place them during a appropriate format prepared for feature extraction.

Fig. 3: Currency Images

Binarisation:
Binarisation of pictures is to convert the given image into binary pictures by victimization the construct of thresholding.
throughout the thresholding method, individual pixels in a picture are marked as object pixels if their worth is bigger than
some threshold worth (assuming Associate in Nursing object to be brighter than the background) and as background pixels
otherwise. This convention is understood as threshold on top of. Variants embody threshold below, that is opposite of threshold
above; threshold within, wherever a element is tagged "object" if its worth is between 2 thresholds; and threshold outside, that is
that the opposite of threshold within. The thresholding is of two types:
Global Thresholding
Local Thresholding
Morphology Filtering
After image binarisation, the digits on the serial numbers of the banknotes often have some discontinuous particles, some
further noise and some unexpected edges. To make the recognition task easier, we apply four morphological transformations to
the binary images. Morphological transformations extract and alter the structure of particles in an image. We applied four binary
processing functions erosion, dilation, opening and closing to remove noise.

All rights reserved by www.ijste.org

609

Identification of Paper Currency Techniques: A Survey

(IJSTE/ Volume 2 / Issue 12 / 109)

Heuristic analysis and Segmentation:

Sometimes there are redundant elements, which do not correspond to proper characters. These elements are not reliably
separable by traditional OCR methods, although they vary in size as well as in contrast, brightness or hue. Since the feature
extraction methods do not consider these properties, there is a need to use additional heuristic analyses to filter non-character
elements. The analysis expects all elements to have similar properties. Elements with considerably different properties are treated
as invalid and excluded from the recognition process. The analysis deals with statistics of brightness and contrast of segmented
characters.
Feature Extraction:
Feature extraction or choice may be a important procedure significantly for currency recognition, that effects on style and
performance of the classifier intensively. If the variations of hand-picked options area unit thus giant, it will simply construct a
classifier with smart recognition performance. it's tough to induce it with the contrary scenario. The essential task of feature
extraction and choice is a way to realize the correspondingly effective options out of the many unfinished options.
Feature types are categorized as follows:
Structural features:
It describes geometrical and topological distinctiveness of a pattern by in lieu of its global and local properties.
Statistical features:
Statistical features are resultant from the statistical division of pixels and describe the characteristic measurements of the pattern.
Global transformation:
Global alteration technique transforms the pixel representation to a more compact form. This reduces the dimensionality of the
feature vector and provides feature invariants to global deformation like translation, dilation and rotation.
IV. PROBLEM IDENTIFICATION
Automated paper currency recognition system can be a very good utility in banking systems and other field of commerce.
Automatic currency note recognition invariably depends on the currency note characteristics of a particular country and the
extraction of features directly affects the recognition ability. We have gone through various literatures, brief comparison among
existing technique we have discussed in earlier section. In this section we explain the some bottleneck of existing system.
Problem in existing system can be easily understandable if we divide identification process as following phases:-

Fig. 3: Different phases of Inage Recognition

YingLi Tian et. Al [IEEE 2014] said that motion blur affects the system performance that is why True recognition rate get
decreases. Problem can be summarized in following points:
1) Motion Blur Problem.
2) Low dimension feature space banknote image.
3) Noise imposed by image capture instrument.
4) Different banknote type.
5) Less efficient feature extraction technique.

All rights reserved by www.ijste.org

610

Identification of Paper Currency Techniques: A Survey

(IJSTE/ Volume 2 / Issue 12 / 109)

V. COMPARISON
Reference
YingLi Tian et. Al
[1]
Masato Aoba[5]
D. A. K. S.
Gunaratna et
al.[6]
Kalyan Kumar
Debnath
et al[7]
Ebtesam Althafiri
et al.[8]
Allah Bux
Sargano et. al.
[15]

Method

Currency Used

Remarks

Accuracy

Component based framework

US

Motion Blur Problem

96%

Radius Basis Function

Euro

Three layer back propagation

Negatively Correlated Neural
Network Ensemble
Multilayer perceptron
Feed-forward Backpropagation
Neural Network (BPN)

Sri Lankan
Currency
Notes
TAKA
(Bangladeshi
currency)
Bahrain Paper
Currency
Pakistani

Three layer perception for classification and RBF for

validation.
Canny algorithm for edge detection and Three layer
back propagation neural network for currency
classification.
Ensemble neural network classifier and trained via
negative correlation learning
Two classifiers, the weighted Euclidean distance using
suitable weights and the Neural Network
Author concluded that efficient feature extraction
technique will improve accuracy of identification
against forged currency

100%
100%

100%
85.1%
99%

Fig. 4: Accuracy Comparison of Various Neural Network Techniques used for Currency Recognition System

VI. CONCLUSION
The difficulty behind large-scale counterfeiting of paper money poses a somber intimidation to our society as huge numbers of
forged notes causes economic volatility. Counterfeiting of bank notes affects the survival of the financial symmetry as its value,
rapidity, output and wellbeing may be affected. Majority of countries that use paper money for transactions are overwhelmed by
this difficulty. In this paper we have gone through different literature which describes different techniques of paper currency
recognition. Finally we have concluded that if we apply some efficient pre-processing and feature extraction technique than we
can improve the accuracy of identification system.
REFERENCES
[1]
[2]
[3]
[4]
[5]
[6]

[7]

Faiz M. Hasanuzzaman, Xiaodong Yang, and YingLi Tian, Senior Member, IEEE Robust and Effective Component-based Banknote Recognition for the
Blind IEEE Trans Syst Man Cybern C Appl Rev. 2012 Nov; 42(6): 10211030.
Ankush Roy, Biswajit Halder, Utpal Garain, David S. Doermann Machine-assisted authentication of paper currency: an experiment on Indian banknotes
Springer 15 May 2015.
Yifeng Liu, Lin Zeng Haar-SVM for Real-time Banknotes Recognition Journal of Information & Computational Science 11:12 (2014) 40314039 August
10, 2014.
Binod Prasad Yadav, C. S. Patil, R. R. Karhe, P.H Patil An automatic recognition of fake India International Journal of Engineering Science and Innovative
Technology (IJESIT) Volume 3, Issue 4, July 2014.
Masato Aoba, Tetsuo Kikuchi, Yoshiyasu Takefuji, Euro banknote recognition system using a three layer perceptron and RBF networks, IPSJ
Transaction on Mathematical Modeling and Its Application, Vol 44, No. SIG 7 (TOM 8), May 2003, Pp. 99-109.
D. A. K. S. Gunaratna, N. D. Kodikara and H. L. Premaratne, ANN Based Currency Recognition System using Compressed Gray Scale and Application
for Sri Lankan Currency Notes-SLCRec, in proceedings of world academy of science, engineering and technology, Nov 2008,vol. 35,ISSN 2070-3740,
Pp. 235-240.
Kalyan Kumar Debnath, Sultan Uddin Ahmed, Md. Shahjahan, A Paper Currency Recognition System Using Negatively Correlated Neural Network
Ensemble, Journal Of Multimedia, December 2010, Vol. 5, No. 6, Pp. 560-567.

All rights reserved by www.ijste.org

611

Identification of Paper Currency Techniques: A Survey

(IJSTE/ Volume 2 / Issue 12 / 109)
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15]

Ebtesam Althafiri, Muhammad Sarfraz, Muhannad Alfarras, Bahraini Paper Currency Recognition Journal of Advanced Computer Science and
Technology Research, June 2012, Vol. 2 No.2, Pp. 104-115.
Pathabe M.S.T. and Bawane N.G., (2011), Feature Extraction Parameters for Genuine Paper Currency Recognition & Verification, International journal of
advanced engineering sciences and technologies.
Dipti Pawade,Pranchal Chaudhari,Harshada Sonkamble
"Comparative Study of Different Paper Currency and Coin Currency Recognition Method"
International Journal of Computer Applications (0975 8887) Volume 66 No.23, March 2013.
Debnath K.K., Ahmed S.U., Shahjahan Md., Murase K., (2010), A Paper Currency Recognition System Using Negatively Correlated Neural Network
Ensemble, Journal of Multimedia, Vols 5(6), 560-567.
Parminder Singh Reel, Gopal Krishan, Smarti Kotwal "Image Processing based Heuristic Analysis for Enhanced Currency Recognition" International
Journal of Advancements in Technology ISSN 0976-4860 Vol 2, No 1 (January 2011).
Hassanpour H., A. Yaseri, G.Ardeshiri, (2007), Feature Extraction for Paper Currency Recognition, International Symposium on Signal Processing and its
Applications (ISSPA), Sharjah, UAE.
Jos M. Bioucas-Dias A New TwIST: Two-Step Iterative Shrinkage/ Thresholding Algorithms for Image Restoration IEEE TRANSACTIONS ON IMAGE
PROCESSING, VOL. 16, NO. 12, DECEMBER 2007.
Allah Bux Sargano, Muhammad Sarfrazb, and Nuhman Haq An intelligent system for paper currency recognition with robust features Journal of Intelligent
& Fuzzy Systems 27 (2014) 1905191.

All rights reserved by www.ijste.org

612