IRJET- Brightness Preserving Bi-Histogram Equalization for Preprocessing in Counterfeit Indian Currency Notes Detection

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 11 | Nov 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 3577
Brightness Preserving Bi-Histogram Equalization for Preprocessing in
Counterfeit Indian Currency Notes Detection
Fathima Hibath Sudheer1, Dr. Priya S2, Mr. Sreekumar K3
1Mtech Student in Image Processing, Model Engineering College, Thrikkakara, Kochi, India
2Professor, Dept. of Computer Engineering, Model Engineering College, Thrikkakara, Kochi, India
3Assistant Professor, Department of Computer Engineering, Model Engineering College, Thrikkakara, Kochi, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract – The rise of color printing technology has
increased the rate of fake currency note printing of identical
notes on a very large scale. Few years back, Indian
government has announced the demonetization of all Rs
500 and Rs 1000, in reserve bank notes of Mahatma Gandhi
series. Indian government has introduced a new Rs 500 and
Rs 2000, to reduce illegitimate activity in India. Even then
the new notes of counterfeit or bogus currency are
distributed in the society. The main purpose of this work is
to identify counterfeit currencies among the real. From the
currency, the strip lines or continuous lines are detected
from real and counterfeit note by using edge detection
techniques. LAB techniques are used to saturate the value of
an input image. This proposed system focuses on pre-
processing stage of the Counterfeit Indian Currency Notes
Detection which includes image adjustment, image filtering
using bilateral filter, image smoothening using Brightness
Preserving Bi-Histogram Equalization (BBHE) and
converting RGB image to LAB color space image.
Key Words: Counterfeit Banknote Detection Methods,
Digital Image Processing Method, Image adjustment,
Image filtering, Smoothening and RGB to LAB
conversion.
1. INTRODUCTION
Research areas for currency are banknote recognition,
counterfeit banknote detection, serial number recognition,
and fitness classification shown in Figure: 1.
Figure 1: Research areas for currency.
Banknote recognition generally concerns with the
classification of banknotes by denomination, i.e., the
currency amount of a note of a specific country. This
classification can also enable recognition of the year of
printing and input direction of the classified
denomination. In some studies, the scope of recognition is
extended to the simultaneous recognition of two or more
Indian currencies.
Counterfeit banknote detection generally concerns with
the methods for distinguishing between genuine and fake
notes.
Banknote serial number is the unique alphanumerical
identifier engraved on each banknote in the banknote
production process. It contains the name of the issuing
bank and the serial information of each denomination. All
banknotes have its own idiomatic serial number and it can
be used to outline its source and circulation route and can
thus be efficiently used to identify counterfeit banknotes.
Fitness classification of the banknotes generally concerns
the methods for classifying banknotes according to their
physical conditions, such as soiling. Banknotes of same
denomination may exhibit fit or unfit conditions, which
include soiling and creases, depending on circulation
intensity and climate conditions. In order to conserve the
robustness of banknotes in circulation, automated self-
service terminals, such as ATMs, need to be equipped with
a fitness classification function to sort out and retrieve
unfit banknotes. Retrieving the unfit banknotes is also
necessary for preventing banknote classification errors.
Within research areas, this work concentrates on
Counterfeit banknote detection. For the last few years, as a
result of the great technological advancement in color
printing, duplicating and scanning, counterfeiting
problems have become more serious. In the past, only the
printing house has the ability to make a counterfeit note,
but today it is possible for any person to print counterfeit
bank notes simply by using a computer and a laser printer
at the home. Therefore the issue of efficiently verifying
counterfeit banknotes from real ones via automatic
machines has become more important. Counterfeit notes
are the problem of almost every country but India has
been hit really hard and has become a very acute problem.
There is a need to design the system that will helpful for

the recognition of paper currency notes with fast speed
and in less time.
The Indian government announced the new rules to
eliminate the bogus currency. The Reserve Bank of India is
the only one that has the full authority to issue banknotes.
There is no proper way to deal with them for a common
person; the common person is also prey to this currency.
Some of the effects that the bogus money has on society
include a reduction in the value of substantial money and
inflation due to more artificial money getting circulated in
the society or the economy, and which in turn dampen our
economy and growth. Then the decrease in the
acceptability of paper money occurs. These are several
techniques used by Reserve Bank of India to identify
artificial currency.
In every year, Reserve Bank of India faces the counterfeit
currency notes or destroyed notes. Handling of the large
volume of counterfeit notes imposes additional problems.
Therefore, involving machines with the assistance to the
human experts makes notes identification process simpler
and efficient. For the detection of forged notes, it needs to
identify the denomination every time they use the device
which consists of ultraviolet light. The bank employees
keep the fake paper currency note on the device and try to
find whether the watermark identification, serial number
and other characteristics of the notes are proper to check
its authentication.
2. RELATED WORKS
B.Sai Prasanthi, D. Rajesh Setty ”Indian Paper Currency
Authentication System using Image processing”[1].In this
article, the authentication of Indian paper currency is
described by applying image processing techniques.
Generally, six features are extracted including
identification mark, security thread, watermark, numeral,
floral design, micro lettering from the image of the
currency. The process begins with image acquisition and
ends at a comparison of features. The system designed is a
low-cost system. The system extracts the features even the
note has scribblings on it. Also, the system will extracts
features even the test image sizes are different when
compared to the reference image.
Rubeena Mirza, Vinti Nanda”Design and Implementation
of Indian Paper Currency Authentication System Based on
Feature Extraction by Edge Based Segmentation Using
Sobel Operator”[2].In this paper, the authentication of
Indian paper currency is described by applying various
image processing techniques. Generally, three features are
extracted including identification mark, security thread,
and watermark from the image of the currency. The
process begins with image acquisition and ends at a
comparison of features. The features are extracted using
edge-based segmentation by Sobel operator and work well
in the whole process with less computation time. The
complete methodology works for the Indian denomination
100, 500 and 1000. The method is very simple and easy to
implement. If the hardware part of image acquisition is
designed then it surely helps us to minimize the problem
of counterfeiting currency.
Sandeep Kaur, Seema Baghla, Sunil Kumar”Enhancement
of Sift algorithm to check the authenticity of Indian
Currency”[3]. SIFT algorithm has been used to analyze the
external features of an image by various researchers in the
past. The currency detection is the application of image
analysis, in which the SIFT algorithm along with the
nearest neighbor classifier has been applied to analyze
external features of the checking the originality of
currency notes. In the present work, a method using the
SIFT algorithm with Bayesian classifier and DWT has been
proposed for checking the originality of currency notes.
The value of Peak signal to noise ratio (PSNR), root mean
square error (RMSE), fault detection rate (FDR) and
accuracy values of the proposed and existing algorithm
(SIFT algorithm with nearest neighbor classifier) are
compared to validate the proposed system. The results
confirmed that the proposed technique is better as
compared to the existing technique for checking the
originality of the currency notes.
Deepak M. P, Prajwala N. B ”Identification of Fake Notes
and Denomination Recognition”[4]. The Indian currency
system has different denominations that are unique in one
feature or the other. These features are color, size or some
identification marks, etc. This system recognizes and
transforms the framework in order to diminish human
energy, and to consequently perceive the measure of the
money esteem and to change over it to different monetary
forms without human supervision. Our proposed work
differentiates white paper and the currency, by detecting
colors of different currencies. We have used a feature
extraction mechanism to identify various identification
patterns and also the denominations in the currency. As
our intention to achieve a simple however productive
calculation that would be helpful for the most extreme
number of monetary standards, using MatLab, we have
developed an efficient system for the monetary standards
10,20,50,100,500 and 2000 which produces 98.8
accuracies.
Prashant Dhar, Md. Burhan Uddin Chowdhury, Tonoy
Biswas ”Paper Currency Detection System Based on
Combined SURF and LBP Features”[5].Proposed a new
paper currency detection system for Bangladeshi paper
currency using combined SURF and LBP features. The
prediction is made by SVM classifier. SVM performs very
well in this case. Paper currency detection is a vital
application for surveillance systems. Very few works have
been done on this application. Here we proposed a new
method to detect paper currency. We considered only
paper currencies of Bangladesh. It is quite a challenging
task to detect currency in different positions from

different environments. This proposed system can detect
currency in rotated positions also. This proposed system
can also calculate the total amount of currency that exists
in an image. We achieved an overall accuracy of 92.6we
will try to improve the performance for the rotated
position of currency. We will focus on folding notes and
overlapped notes. We will try to consider all possible sorts
of notes. Moreover, we should investigate with other local
or global features so as to improve performance better.
Navya Krishna G, Sai Pooja G, Naga Sri Ram B, Yamini
Radha V, Rajarajeswari P ”Recognition of Fake Currency
Note using Convolutional Neural Networks”[6].In this
paper, proposed a model which demonstrates the
feasibility of using CNN with the VGG 16 architecture.
Although the generated data set was small and did not
represent the real-world scenario of counterfeit currency
data-set, it was very helpful throughout the experiment.
The process of detection of fake notes is quick and easy
under the trained model. By this, we can also assure that
under real and large data set, the model AFCRS can be
well-trained and also provides accurate results, which can
help the people in recognizing the currency note whether
it is counterfeit or original. Future research may include
the deployment of the model in smartphones as an
application and make society and people more
comfortable in recognizing counterfeit currency. This
model can also be compared with various architectures of
CNN which may have a low error rate than the present
model and can be combined by applying image pre-
processing techniques like and edge-detection to crop the
currency note out of an image which will present better
results.
Fumiaki Takeda and Sigeru Omatu” High Speed Paper
Currency Recognition by Neural Networks”[7]. In this
paper, we have applied NN to paper currency recognition
and showed the effectiveness compared with a
conventional manual method. Furthermore, we have
proposed a structure reduction method of the NN using
random masks and showed its effectiveness for time series
data and its Fourier power spectra. Finally, we also
introduced a new evaluation method for reliability and
showed its effectiveness using real data. We expect that
the present method will promote compactness, high-speed
transaction, and low cost of paper currency recognition
machines.
Gouri Sanjay Tele, Akshay Prakash Kathalkar, Sneha
Mahakalkar, Bharat Sahoo, Vaishnavi Dhamane ”Detection
of Fake Indian Currency”[8].In this paper, a technique for
verifying Indian paper currency. The approach gives an
efficient method for fake currency detection based on
physical appearance. The work will surely be very useful
for minimizing the counterfeit currency. Through this
application, we are able to see the missing parameters
which the fake note doesn’t have as compared to the
original notes. Original Currency is being detected using
the Image Processing Technique.
3. COUNTERFEIT BANKNOTE DETECTION
3.1 Counterfeit Banknote Detection Methods:
Figure 2: Counterfeit banknote detection methods
A. Commonly Used Method for Detecting Fake Currency
1. See-through Register
The small floral design printed on both front (hollow) and
back (filled up) of the note in the middle of the vertical
band next to the Watermark has an accurate back to back
registration. The design will appear as the floral design
when seen against the light.
2. Watermarking
The Mahatma Gandhi Series of the banknotes include the
Mahatma Gandhi watermark with a light and shade effect
and multi-directional lines in the watermark window.
3. Fluorescence
Number panels of the notes are printed in the fluorescent
ink. The notes also have optical fibers. Both can be seen
when the notes are exposed to the ultra-violet lamp.
4. Security Thread
The Rs.500 and Rs.100 notes have a security thread with
the similar visible features and inscription “Bharat” (in
Hindi), and “RBI”. When held against the light, the security
thread on Rs.2000, Rs.500 and Rs.100 can be seen as one
continuous line. The Rs.5, Rs.10, Rs.20, and Rs.50 notes
contain a readable, fully embedded windowed security
thread with inscription “Bharat” (in Hindi), and “RBI”. The
security thread appears on the left of the Mahatma's
portrait.

5. Intaglio Printing
The portrait of Mahatma Gandhi, the Reserve Bank seal,
guarantee and promise clause, Ashoka Pillar Emblem on
the left, RBI Governor's signature is printed on intaglio i.e.
in raised prints, which can feel by touch, in Rs. 20, Rs. 50,
Rs. 100, Rs.500 and Rs.2000 notes.
6. Latent image
On the opposite side of Rs.2000, Rs.500, Rs.100, Rs.50 and
Rs.20 notes, a vertical band on the right side of the
Mahatma Gandhi’s portrait contains a latent image
showing the respective denominational value in the
numeral. The latent image is apparent only when the note
is held horizontally at eye level.
7. Micro lettering
This feature sees between the vertical band and Mahatma
Gandhi portrait. It always contains the word "RBI‟ in Rs.5
and Rs.10. The notes of Rs.20 and above also hold the
denominational value of the notes in micro letters. This
feature can see well under a magnifying glass.
8. Identification Mark
Each note has a unique mark. A special feature in intaglio
has been presented on the left of the watermark window
on all notes except Rs.10/- note. This feature is in different
shapes for different denominations (Rs.20-Vertical
Rectangle, Rs.50- Square, Rs.100-Triangle, Rs.500-Circle,
and Rs.1000- Diamond) and helps the visually impaired to
identify the denomination.
9. Optically Variable Ink
This is a new feature included in the Rs.2000 and Rs.500
notes with revised color scheme. The numeral 2000 and
500 on the opposite of Rs.2000 and Rs.500 notes
respectively are printed in optically variable ink viz., a
color-shifting ink. The color of the numeral 2000/500
appears green when the note is held flat but would change
to blue when the note is held at an angle.
B. Digital Image Processing Method for Detecting
counterfeit Currency.
Design flow of the counterfeit currency detection system
includes eight stages: Image acquisition, pre-processing,
gray scale conversion, edge detection, image
segmentation, feature extraction, comparison and output
[9]. This system works on two images, one is testing
currency image on which authentication is to performed
and the other is the original currency image.
1. Image Acquisition
There are various ways to acquire images such as with the
help of a camera or scanner. The acquired image should
retain all the features [9].
2. Pre-Processing
Pre-processing of the image is those operations that are
normally required prior to the main data analysis and
extraction of information. The aim of image pre-
processing is to suppress undesired distortions or to
enhance some image features that are important for
further processing or to analysis. It includes:
2.1 Image Adjusting
When we get the image from a scanner, the size of the
image is too big. In order to reduce the calculation, we
decrease the size of the image. Image Adjusting is done by
using image interpolation. Interpolation is the technique
mostly used for tasks such as zooming, rotating, shrinking,
and geometric corrections.
2.2 Image smoothening
While using a camera or a scanner and perform image
transfers, some noise will appear on the image. Image
noise is the random variation of the brightness in images.
Removing the noise is a major step when image processing
is being performed. Although, noise may affect
segmentation and pattern matching. When performing the
smoothing process on a pixel, the neighbor of the pixel is
used to do some transforming. After that, the new value of
the pixel is created. The neighbor of the pixel is consisting
of some other pixels and they build up a matrix, the size of
the matrix is an odd number, the target pixel is located on
the middle of the matrix. Convolution is used to perform
image smoothing. Image smoothening can also be done
with the help of a median filter which gives more effective
than convolution when the goal is to simultaneously
reduce the noise preserving edges. The median filter
replaces a pixel via the median pixel of all the
neighborhoods [9].
3. Gray-scale conversion
The image acquired is in RGB color. It is converted into
gray scale because it carries only the intensity information
which is easy to process instead of processing three
components R (Red), G(Green), B(Blue) [1].
4. Edge detection
Edge detection is an essential technique in image
processing and computer vision, particularly in the areas
of feature detection and feature extraction, which aims at
identifying points in a digital image at which the image
brightness alters sharply or, more formally, has

discontinuities. Edge detection is one of the major steps in
image processing, image analysis, image pattern
recognition, and computer vision techniques [8].
5. Image segmentation
Image segmentation sub divides the image into its
component regions or objects. A level to which sub
division is carried depends on problem being solved.
Segmentation algorithm for monochrome images
generally based on one of the two basic properties of
image intensity values:
• Discontinuity
• Similarity.
The approach in the first category is to partition an image
based on abrupt changes in intensity such as edges in an
image. The approach in the second category is based on
partitioning an image into regions that are similar
according to a set of predefined criteria [8].
6. Feature Extraction
In pattern recognition and in image processing, feature
extraction is the special form of dimensionality reduction
method. This method captures the visual content of
images for indexing and retrieval. If input data to an
algorithm is too large to be processed and it is assumed to
be notoriously redundant (much data but not much
information) then the input data will be converted into a
reduced representation set of features (also named feature
vector). If attributes are extracted are chosen carefully, it
is expected that the attributes set will extract the relevant
information from the input data in order to perform the
desired task using this reduced representation instead of
using the full-size input. Feature extraction involves
simplifying the number of resources required to describe
the large set of data.
Visual attributes of images are of two types:
 Domain-specific attributes include fingerprints,
human faces.
 General attributes include color, texture, and
shape.
Figure 2: Flow Chart of Digital Image Processing Method to
Detect Fake Notes.
There are two types of attributes distinguish under the
shape attribute extraction:
• Global attributes include moment invariant,
aspect ratio and circularity.
• Local attributes include boundary segments [1].

Figure 3: Feature Extraction Approach
7. Comparison
Finally, the extracted features of test currency image are
compared with the extracted features of the original
currency image, if it matches then the currency is original
otherwise fake [1].
C. MATLAB technique:
In this technique, one can split red, blue, green components
of a picture and name them as r1, g1, b1 which correspond
to image i.e. original currency note. Consider the second
image that is noted to be tested. Split this image to
components r2, b2, g2. Construct a new image with
components as r1, g2, b1 or r2, g1, b1 or b2, g1, b1. But
r1,g2,b1 combination is most preferred because the human
eye is sensitive to green component and most of our
images contain maximum green component so that our
output image will be much easier to identify counterfeit
note more effectively. After that compare newly
constructed images with image1. Calculate the threshold
value of equivalence by calculating the standard deviation.
If equivalence is above 40% then one can consider it as an
original note. Here consider 40% of the value because note
may be damaged. Parameters for a measure of comparing
images are Mean Square Error (MSE), Peak Signal to Noise
Ratio (PSNR in dB), and structural Content (SC). When
combining two various components of two images then if a
note to be tested is original then only at the place of a
number we get variation. But in case of fake note after
applying the same code, one can observe that the image
overlapping is not done correctly. One can also see that the
resultant image is blurred indicating fake note. So one can
confirm that it is a fake note [12].
D. Counterfeit Detection Pen:
A counterfeit pen is simply an inexpensive device that is
designed to determine if a currency note is original or fake.
The pen includes a tincture of iodine as ink which, when
drawn over a note, will remain amber or brown. According
to the manufacturer, the ink will turn black if the note is
fake.
1. Working of counterfeit pen:
The iodine in the pen respond with starch, which is the
primary component that makes a white paper look
brighter. Most corporate paper, made from wood pulp, is
brown unless bleached and starched. If there is no
presence of starch in the paper then the pen will indicate -
by remaining amber- that the note is original.
2. How counterfeiters defeat this pen:
The iodine in the pen respond with starch that makes
white paper look brighter. Most unless bleached and
starched. If there is no starch present in the paper then the
pen will indicate – by remaining amber - that the note is
original [12].
E. Other techniques:
Another anti-counterfeit device for the money is an
Ultraviolet counterfeit detection scanner. Best used in the
highly lit point of sale locations, the UV detector identifies
ultraviolet security features present in most currencies. By
simply placing the note in the detector, counterfeit
currency is immediately identified, without the need for an
employee to closely examine the note [12].
These are the different techniques for counterfeit banknote
detection. The most efficient technique is digital image
processing method.
4. PROPOSED SYSTEM
The steps involved in Image Enhancement for Fake Indian
Currency Notes Detection are shown in figure 4.
Figure 4: Block diagram for proposed system.

4.1 Input Image:
In this first stage of any vision system is the input image
stage. After the image has been obtained, the various
methods of processing can be applied to the image to
perform many different tasks. Performing input images in
image processing is always the first step in the workflow
sequence because, without an image, no processing is
possible. There are various techniques to acquire images
such as with the help of a camera or scanner. The input
image should retain all the features. Here input image is
the RGB image of currency taken under the UV light.
4.2 Image Adjustment:
Image Adjusting is one of the most pre-processing
techniques, which is done with the help of image
interpolation. Interpolation is the technique widely used
for tasks such as zooming, rotating, shrinking, and
geometric corrections. Removing the noise is a major step
when image processing is being performed. However, the
noise may affect segmentation and pattern matching.
When performing the smoothing process on a pixel, the
neighbor of the pixel is used to do some transforming.
After that, a new value of the pixel is created [13].
4.3 Image Filtering:
In this system, filtering is done for removing noise. Here
the bilateral filter is used for noise removal. It is a non-
linear, edge-preserving and noise-reducing smoothing
filter for images. It substitutes the intensity of each pixel
with the weighted average of intensity values from the
nearby pixels. This weight can be based on Gaussian
distribution. Crucially, the weights depend not only on
Euclidean distance of the pixels but also on the
radiometric differences (e.g., range differences, such as
color intensity, depth distance, etc.). This preserves the
sharp edges.
4.4 Image Smoothening:
Smoothening is done using Brightness Preserving Bi-
Histogram Equalization (BBHE). BBHE firstly decomposes
an image into two sub-images based on the mean of the
input images. One of the sub-images is the set of samples
less than or equal to the mean whereas the other one is
the set of samples greater than the mean. Then the BBHE
equalizes the sub-images independently based on their
respective histograms with the constraint that the samples
in the formal set are mapped into the ranges from the
minimum gray level to the input mean and the samples in
the latter set are mapped into the ranges from the mean to
the maximum gray level. In other words, one of the sub-
images is equalized over the range up to the mean, based
on the respective histogram. Thus, resulting equalized
sub-images are bounded by each other around the input
mean, which has an effect of preserving mean brightness.
Figure 5: BBHE algorithm
4.5 RGB to LAB Color Space Conversion:
The next implementation in the proposed method is to
convert the RGB color space to L*a*b* color space. For this
proposed work L*a*b* color space is selected which is a
homogeneous space for visual perception. The difference
between the two points in the L*a*b* color space is the
same as the human visual system. Since the L*a*b* model
is a three-dimensional model, it can only be represented
properly in three-dimensional space [14] - [2]. The
solution to convert digital images from the RGB space to
the L*a*b* color space is given by the following formula
[14].
L* = 116 f(Y/Yn) – 16
a* = 500[f(X/Xn)-f(Y/Yn)]
b* = 200[f(Y/Yn)-f(Z/Zn)]
X, Y, Z, Xn, Yn, and Zn are coordinates of CIEXYZ Color
space. The solution to convert the digital images from the
RGB space to the CIEXYZ color space is the following
formula.

X 0.608 0.174 0.201 R
Y = 0.299 0.587 0.114 G
Z 0.000 0.066 1.117 B
Xn, Yn, and Zn respectively correspond to the white value
of the parameter.
F(x) = X^1/3 x>0.008856
7.787x+16/116 x<= 0.008856
Color space conversion is translation of the representation
of a color from one basis to another. This typically occurs
in context of converting an image that is represented in
one color space to another color space.
5. EXPERIMENTAL RESULTS
In this project, the RGB image of currency note is given as
input image and various preprocessing methods has been
applied such as Bilateral filtering , Brightness Preserving
Bi-Histogram Equalization (BBHE) and then converted
equalized image to LAB color space.
Figure 6: Noise removal using bilateral filtering
Figure 7: Histogram Equalization.
Figure 8: Brightness Preserving Bi-Histogram Equalization
Figure 9: Converting equalized RGB image to LAB color
space.
6. CONCLUSION
Pre-processing is a necessary step in any computer vision
system, which includes extraction of information from the
RGB image taken under UV light. According to the
requirement, various different pre-processing techniques
are used and developed. In this proposed work, we use
different pre-processing methods such as image
adjustment, image filtering using the bilateral filter, image
smoothening using Brightness Preserving Bi-Histogram
Equalization (BBHE) and converting RGB image to LAB
color space image. This system provides better
performance for processing than the existing method.
REFERENCES
[1] Rubeena Mirza, Vinti Nanda ”Design and
Implementation of Indian Paper Currency
Authentication System Based on Feature Extraction by
Edge Based Segmentation Using Sobel Operator”
International Journal of Engineering Research and
Development e-ISSN: 2278-067X, p-ISSN: 2278-800X,
www.ijerd.com Volume 3, Issue 2 (August 2012), PP.
41-46.
[2] Sandeep Kaur,Seema Baghla, Sunil Kumar
”Enhancement of Sift algorithm to check authenticity
of Indian Currency” International Journal of

Computational Intelligence Research ISSN 0973-1873
Volume 13, Number 5 (2017), pp. 945-953 c
Research India Publications
http://www.ripublication.com
[3] Prashengit Dhar, Md. Burhan Uddin Chowdhury,
Tonoy Biswas ”Paper Currency Detection System
Based on Combined SURF and LBP Features” 2018
2nd Int. Conf. on Innovations in Science, Engineering
and Technology (ICISET) 27-28 October 2018,
Chittagong, Bangladesh.
[4] Navya Krishna G, Sai Pooja G, Naga Sri Ram B, Yamini
Radha V, Rajarajeswari P ”Recognition of Fake
Currency Note using Convolutional Neural Networks”
International Journal of Innovative Technology and
Exploring Engineering (IJITEE) ISSN: 2278-3075,
Volume-8 Issue-5 March, 2019
[5] G Chinmay Bhurke, Meghana Sirdeshmukh, Prof. Mrs.
M.S.Kanitkar ,“Currency Recognition Using Image
Processing s,” International Journal of Innovative
Research in Computer and Communication
Engineering,, vol.III, May 2015 .
[6] https://www.overleaf.com/project/5dc917fb52bc02
0001f5387d K. Kang ;C. Lee], Fake banknote detection
using multispectral images,’ International Conference
on Information, Intelligence, Systems Applications
(IISA), 19 December 2016.
[7] Binod Prasad Yadav, C. S. Patil, R. R. Karhe, P.H Patil,
An automatic recognition of fake Indian paper
currency note using MATLAB,” International Journal
of Engineering Science and Innovative Technology
(IJESIT) Volume 3, Issue 4, July 2014
[8] D.Alekhya ,G.DeviSuryaPrabha , G.VenkataDurgaRao,
Fake Currency Detection Using Image Processing and
Other Standard Methods”, International Journal of
Technology, may 2015.
[9] Amol A. Shirsath and S. D. Bharkad, Survey Of
Currency Recognition System Using Image Processing,
International Journal of Computational Engineering
Research, Vol, 03, Issue 7M. Young, The Technical
Writer’s Handbook. Mill Valley, CA: University Science,
1989.
[10] Rubeena Mirza and Vinti Nanda, Paper Currency
Verification System Based on Characteristic Extraction
Using Image Processing, International Journal of
Engineering and Advanced Technology (IJEAT) ISSN:
2249 – 8958, Volume-1, Issue-3, February 2012.
[11] PM.Deborah., PC.Soniya Prathap, “Detection of Fake
currency using Image processing,” IJISET -
International Journal of Innovative Science,
Engineering Technology, vol I, 10 December 2014.
[12] Chun Chen;“Computer image processing technology
and algorithms”., Beijing: Tsinghua University Press,
2003.
[13] R. Fisher, K Dawson-Howe, A. Fitzgibbon, C.
Robertson, E. Trucco (2005). Dictionary of Computer
Vision and Image Processing. John Wiley. ISBN 0-470-
01526-8.
[14] G Chinmay Bhurke, Meghana Sirdeshmukh, Prof. Mrs.
M.S.Kanitkar ,“Currency Recognition Using Image
Processing s,” International Journal of Innovative
Engineering,, vol.III, May 2015 .
[15] Sagar S. Lawade, Gayatri S. Hedau, Apurva C.
Ramgirwar, Fake Currency detection using image
processing,” International Journal of Research in
Computer and Communication Technology, vol III,
may 2014

IRJET- Brightness Preserving Bi-Histogram Equalization for Preprocessing in Counterfeit Indian Currency Notes Detection

More Related Content

What's hot (7)

Similar to IRJET- Brightness Preserving Bi-Histogram Equalization for Preprocessing in Counterfeit Indian Currency Notes Detection (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Brightness Preserving Bi-Histogram Equalization for Preprocessing in Counterfeit Indian Currency Notes Detection