1. “Currency Recognition System
using SIFT Feature
Descriptor”
SUBMITTED BY –
1. SHUBHAM NIJHAWAN (44614802817)
2. DAKSH AHUJA (45814802818)
3. UTKARSH KUMAR (45914802818)
2. OBJECTIVE:
We are proposing a system for automated currency recognition. Our method can be used
for recognizing both the country of origin as well as the denomination and value of a
given banknote. Only paper currencies have been considered. This method works by first
identifying the country of origin using certain predefined areas of interest, and then
extracting the denomination value using characteristics such as size, colour, or text on the
note, depending on how much the notes within the same country differ. We will also use
this to check whether the currency is real or fake.
It is difficult for people (eg. who work for the money exchanging) to recognize
currencies from different countries. Our aim is to help people figure out this problem.
4. SIFT ALGORITHM
The Scale-Invariant feature transform(SIFT) is an algorithm to detect
and describe local features in images. For any object is an image
,interesting points on the object can be extracted to provide a “feature
description” of the object. This description, extracted from a training
image, can then be used to identify the object when attempting to locate
the object in a test image containing many other objects.
7. DATA FLOW DIAGRAM
The methodology of this project is extracting unique features of the
currency note using grid. Grid divides the currency into nine parts on
each side which helps to reduce the time complexity of the proposed
model. Applying the preprocessing to each block to recognize and
extract potential feature of currency note.
8. CODE:
In this module we are provided with few datasets (currency
notes) and further we are analyzing that the inputs that we
have taken are converted into gray scale and differentiated as
per the key points like color detection,identification of the
country,size etc in the pre-processing phase .Further,the
currency taken is compared with the datasets present in the
system and finally, the output will be the currency which has
the maximum match from all the datasets provided.
9.
10.
11.
12. FUTURE PERSPECTIVE
# All Currency Detection: Being rational, we are going to upgrade our project
in a way that it will be able to check for other currencies as well apart from
Indian currency.
# Making an algorithm that will provide the Indian value of currency : We
are a going to create a way in which the given currency denomination will be
converted into its Indian value.