Indian Currency Detection for blind people with VGG16
Author(s):
Nitin Momaya, Kulkarni Abhilash Mahesh, Mahtasham Abbas, Shradha Nanda
Keywords:
Currency Detection, VGG16, Indian Currency, Currency Notes
Abstract
In spite of the immense use of master cards and other electronic modes of payment, there hasn't been any kind of reduction in the use of money for ordinary exchanges owing to the ease and convenience factor. This exchange of money poses a serious problem to the visually impaired people who are unable to identify the different currency notes. This is because every currency note has the same feel without any brail markings on it. In this project we aim to provide a vision [1]-based framework that is responsible for detecting and recognizing the Indian currency notes. There are a lot of drawbacks in the existing system and hence our proposed system will extract attributes from bank notes using deep learning algorithm. A Convolutional Neural Network (CNN) is basically a Deep Learning algorithm that can take an input image of the banknote and it can assign importance (learnable weights) to different objects of the image and thus it will be able to differentiate one currency note from the other.[3] The existing system uses Alex Net which can only extract less features. The model used in our project is VGG16 which has the capability of extracting deep features from the currency notes. The proposed system can help blinds to even recognize the currency notes that have been worn out with its continuous usage over a period of time. Our proposed system can help classifying notes with a greater efficiency of 99.07%. This system helps to curtail the number of frauds happening with visually impaired in the country and thereby reducing their dependency on others.
Article Details
Unique Paper ID: 152154

Publication Volume & Issue: Volume 8, Issue 2

Page(s): 541 - 544
Article Preview & Download


Share This Article

Conference Alert

ICM - STEP

International conference on Management, Science, Technology, Engineering, Pharmact and Humanities.

Go To Issue



Call For Paper

Volume 7 Issue 9

Last Date 25 February 2020

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies