You are on page 1of 5

DIGITAL IMAGE PROCESSING PROJECT

CURRENCY RECOGNITION SYSTEM USING IMAGE


PROCESSING

Team Members

M.AKSHAY (2013506060)

M.MIHASH KHAN (201 3506085)


ABSTRACT:
It is difficult for people to recognize currencies from different countries. Our aim is
to help people solve this problem.
However, currency recognition systems that are based on image analysis entirely
are not sufficient.
Our system is based on image processing and makes the process automatic and
robust.
Color and shape information are used in our algorithm.
A reliable currency recognition system could be used in any sector wherever
monetary transaction is of concern.

For example, the staffs who work for the money exchanging (e.g. Forex Bank)
have to distinguish different types of currencies and that is not an easy job.

They have to remember the symbol of each currency.

This may cause some problems (e.g. wrong recognition), so they need an efficient
and exact system to help their work.

EXISTING SOLUTION:
There are already some papers related to Currency Recognition System using
image processing. The papers are:

 http://www.diva-portal.org/smash/get/diva2:324361/ FULLTEXT02

PROPOSED SOLUTION:

The solution is we use image processing software to find the face present in each
currency and then their eyes are extracted from the face. We use image processing
softwares like MATLAB which helps us to segment, enhance and make the image
help us get the details and makes our evaluation easy.
Here we train the software by adding many currencies so that the system exactly
identifies the face and their eyes present in the currencies. Then the serial numbers
present in the currency can be extracted from the image using Optical Character
Recognition.

MATLAB CODE:
USING CASCADE OBJECT DETECTOR:
1. Face Detection:

FDetect = vision.CascadeObjectDetector('FrontalFaceLBP','MinSize',[60 60]);


BB = step(FDetect,I);
Face=imcrop(I,BB);
figure,imshow(Face);
title('Face');

INPUT OUTPUT

2. Eye Detection:

EyeDetect = vision.CascadeObjectDetector('EyePairBig','MergeThreshold',1,
'MinSize',[11 45],'MaxSize',[20 50]);
BB=step(EyeDetect,I);
Eyes=imcrop(I,BB);
figure,imshow(Eyes);
title('Eye');
INPUT OUTPUT

EXTRACTING STRINGS FROM IMAGES:

%Read the input image


I=imread('American Dollar.jpg');
% Convert to binary image
threshold = graythresh(a);
imagen =~im2bw(a,threshold);
% Label connected components
[L ,Ne]=bwlabel(imagen);
% Measure properties of image regions
propied=regionprops(L,'BoundingBox');
hold on
% Plot Bounding Box
for n=1:size(propied,1)
rectangle('Position',propied(n).BoundingBox,'EdgeColor','g','LineWidth',2)
end
hold off
pause (1)
% Objects extraction
figure
for n=1:Ne
[r,c] = find(L==n);
n1=imagen(min(r):max(r),min(c):max(c));
imshow(~n1);
pause(0.5)
end
INPUT OUTPUT

REFERENCES:

For matlab commands,

 http://in.mathworks.com/help/matlab/ref/rgb2gray.html

 http://in.mathworks.com/help/vision/ref/vision.cascadeobjectdetector-
class.html

 http://in.mathworks.com/help/matlab/creating_plots/the-image-object-and-
its-properties.html

You might also like