Вы находитесь на странице: 1из 11

Currency Recognition

using Image Processing


AMANDEEP SRIVASTAVA
Why currency THERE ARE AROUND 200+ DIFFERENT
CURRENCIES USED IN DIFFERENT
COUNTRIES AROUND THE WORLD. SO IT
recognition? BECOMES DIFFICULT FOR ONE TO
REMEMBER ALL THOSE CURRENCIES. THIS
PROJECT HELPS IN RECOGNIZING INDIAN
DENOMINATIONS OF RS.10 , 20 AND 100.
IT IS ALSO USEFUL FOR BLIND PEOPLE WHO
FACE PROBLEMS IN RECOGNIZING THE
DENOMINATIONS.
Steps Involved

Taking a photo of the denomination using a camera.


Reading that image into Matlab.
Separate image background and foreground.
Applying Colour Histogram technique.
Output the result.
Taking the photo
of denomination
The image is taken using mobile phone
camera.
Taking the photo of denomination

The image is taken under proper lighting conditions.


No occlusion or shadowing is there and image is taken in a clear
environment.
Distance of camera is nearly fixed from the object and within a small
range of variation.
The orientation of the currency notes was such that the sufficient amount
of data required for further processing of even a single face was at least
visible.
The currency notes are of good quality i.e. they are not very much full of
stains or dust etc
Separating Background and
Foreground

We convert the read image into grayscale form.


We use canny edge detection on the grayscale image.

WHY CANNY EDGE DETECTION ?


The Canny operator uses two thresholds to detect strong and weak edges. It
includes the weak edges in the output only if they are connected to strong
edges. As a result, the method is more robust to noise, and more likely to
detect true weak edges.
Image after
separating
background part
The white background of image is
removed and it is cropped to the
denomination region.
Separating Background and
Foreground (Contd.)

Apply scan line algorithm on the image after edge detection.


The number of pixels present in each line is counted while the image is
scanned from left to right line by line.
The line that contains the number of pixels greater than the set threshold is
highlighted.
The threshold used to mark the line here is set after a lot of experiments
performed with different thresholds on the given set of currency notes.
Finally, we have a distinct area produced by the intersection of both the
scans.
Colour Histogram Technique

We find standard deviation of all pixel of RGB of input image with all the
images that are present in our database.
We design the histogram chart for all R,G and B values of the input image.
Histogram chart has pixel value (0-255) on the X axis and number of pixels
(0-image size) corresponding to that colour value on the Y axis.
We divide the X axis in 10 equal parts and make a vector of each and
then find standard deviation with images in our database.
1
=
=1 xi

The image in our database with minimum is the input image.


Final Result
The value of input denomination pops up.
Thank you

Вам также может понравиться