Authors :
Riddhi Shinde; Aishwarya Thorat; Aditi Yadav; Jyoti Singh; Rahul Jiwane
Volume/Issue :
Volume 8 - 2023, Issue 4 - April
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://bit.ly/3pioQjP
DOI :
https://doi.org/10.5281/zenodo.7902617
Abstract :
- The printing and scanning industry has made
significant technological advancements, but
unfortunately, thishas also led to a rise in counterfeiting.
Counterfeit currency cannegatively impact the economy
and reduce the value of genuine money. Therefore,
detecting fake currency is crucial. Traditional methods
have relied on hardware and image processing
techniques, which can be inefficient and timeconsuming. To address this issue, we have proposed a
new approach that uses a deep convolutional neural
network to detect counterfeit currency. Our method
analyzes currency images and can efficiently identify
fake currency in real time. We trained a transfer learned
convolutional neural network using a dataset of two
thousand currency notes to learn the feature map of
genuine currency. Once the feature map islearned, the
network is able to identify counterfeit currency quickly
and accurately. Our proposed approach is highly
effective and significantly reduces the time required to
identify fake currency among the 500 notes in our
dataset.
- The printing and scanning industry has made
significant technological advancements, but
unfortunately, thishas also led to a rise in counterfeiting.
Counterfeit currency cannegatively impact the economy
and reduce the value of genuine money. Therefore,
detecting fake currency is crucial. Traditional methods
have relied on hardware and image processing
techniques, which can be inefficient and timeconsuming. To address this issue, we have proposed a
new approach that uses a deep convolutional neural
network to detect counterfeit currency. Our method
analyzes currency images and can efficiently identify
fake currency in real time. We trained a transfer learned
convolutional neural network using a dataset of two
thousand currency notes to learn the feature map of
genuine currency. Once the feature map islearned, the
network is able to identify counterfeit currency quickly
and accurately. Our proposed approach is highly
effective and significantly reduces the time required to
identify fake currency among the 500 notes in our
dataset.
