Fake Note Detection System Based On CNN Algorithm & Image Processing
Fake Note Detection System Based On CNN Algorithm & Image Processing
'y'^l*'v-
\5\vl. '- MASTER oF coMpurER AppLrcArroNS <
r^.l-- .1
' lIV
\M lV In
.'MPUTERSCIENCE & ENGINEERTNG ^t,
*.a
s
rr,^AruJ'
It I !
1 lV l/ BABU 7l V
''NKESULA
' C, ,
.r/
(r9oo1Foo33)
Y) {.'-
Under the guidance of 1
D
D.
ffiu*'J
;;J pd4 €ffib
@@
L'
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
ANANTAPURAMU-s15002
ANDHRA PRADESH
2021-2022
l./
l<Y/
Signature of H.O.D
The advancement of color printing technology has increased the rate of fake indian
cunency 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 cunency 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. We need a system that find out the
currency note is real note or fake note. For detecting the real or fake note we use
Convolutional Neural Network algorithm and image processing these are used to perform
data processing and data extraction that gives accurate result.
In the existing system, to identify the currency note is real or fake it uses K-Nearest
Neighbours. KNN used for data processing when you have a snrall dataset and the data is
noise free and labeled. KNN algorithm does not perform well on large datasets the result of
KNN algorithm is limited as the data set used was quite small. when considered in the real-
world scenario it does not perform as well as it has currently. Because of large data sets
The development of proposed system would assess the features of fake note and real
note. In the advanced age of computer science and high computational methods, various
machine learning algorithms are introduced by image processing that gives the fake identity
of the cuffency. Detection and recognition methods over the algorithm include entities like
color, shape, paper width and image filtering on the note. Developing a method for fake
currency recognition based on Convolutional Neural Network followed by image processing.
It automatically detects the irnportant features without any human supervision.. This system
identify the fake note and real note fast. It will express the output through text and audio, like
the value of the note and it is fake or real.