Vision Impairment has been treated as a deterrent to normal functioning in human beings, so for such people, it is difficult to recognize the notes. The current system uses Malaysian Ringgit banknotes and extracts RGB values from the banknotes. The algorithms used were KNN, SVM, Naive Bayes, Decision Tree, and deep learning Alexnet. The proposed system uses Indian Currency and is divided into 3 phases. In phase I four features are extracted, phase II RGB values are extracted, and finally, in phase III, phase I and phase II are concatenated to produce better results. The algorithms used are KNN, Decision tree, SVM, Naive Bayes and deep learning VGGnet. Our system provides an accuracy of 98 percent in KNN, 95 percent in Decision Tree, 100 percent in SVM and 90 percent in Naive Bayes

Banknote Recognition, Deep Learning, Machine Learning

[1] Snigdha Kamal, Simarpreet Singh Chawla, Nidhi Goel, and Balasubramanian Raman, ?Feature extraction and identification of indian currency notes?, In 2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), pages 1?4, IEEE, 2015.
[2] Gouri Sanjay Tele, Akshay Prakash Kathalkar, Sneha Mahakalkar, Bharat Sahoo, and Vaishnavi Dhamane, ?Detection of fake indian currency?, International Journal of Advance Research, Ideas and Innovations in Technology, 4(2):170?176, 2018.
[3] Naga Sri Ram B Yamini Radha V Rajarajeshwari P Navya Krishna G, Sai Pooja G, ?Recognition of fake currency note using convolutional neural networks?, 4(2):182?186, 2018.
[4] NAJ Sufri, NA Rahmad, NF Ghazali, N Shahar, and MA As?ari, ?Vision based system for banknote recognition using different machine learning and deep learning approach?, In 2019 IEEE 10th Control and System Graduate Research Colloquium (ICSGRC), pages 5?8, IEEE, 2019.
[5] Carlos M Costa, Germano Veiga, and Armando Sousa, ?Recognition of banknotes in multiple perspectives using selective feature matching and shape analysis?, In 2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC), pages 235?240, IEEE, 2016.
[6] NA Jasmin Sufri, NA Rahmad, MA As?ari, NA Zakaria, MN Jamaludin, LH Ismail, and NH Mahmood, ?Image based ringgit banknote recognition for visually impaired?, Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(3-9):103?111, 2017.
[7] Hemant Kumar Soni, ?Machine Learning a?C? A New Paradigm of AI,? ?International Journal of Scientific Research in Network Security and Communication?, Vol.7, Issue.3, pp.31-32, 2019.
[8] Jesse Davis and Mark Goadrich, ?The relationship between precision, recall and roc curves?, In Proceedings of the 23rd international conference on Machine learning, pages 233?240, 2006.
[9] B. Sun and J. Li, ?The recognition of new and old banknotes based on svm?, In 2008 Second International Symposium on Intelligent Information Technology Application, volume 2, pages 95?98, 2008.
[10] Z. Solym?ar, A. Stubendek, M. Radv?anyi, and K. Karacs, ?Banknote recognition for visually impaired?, In 2011 20th European Conference on Circuit Theory and Design (ECCTD), pages 841?844, 2011.
[11] Miha Vuk and Tomaz Curk, ?Roc curve, lift chart and calibration plot? Metodoloski zvezki, 3(1):89, 2006.
[12] Rohini M., Arsha P., ?Detection of Microaneurysm using Machine Learning Techniques,? International Journal of Scientific Research in Network Security and Communication, Vol.7, Issue.3, pp.1-6, 2019.
[13] Smita D. Raut, S. A. Thorat, ?Deep Learning Techniques: A Review?, International Journal of Scientific Research in Computer Science and Engineering, Vol.8, Issue.1, pp.105-109, 2020.
[14] Oluwabunmi Ayankemi ONI , ?A Framework for Verifying the Authenticity of Banknote on the Automated Teller Machine (ATM) Using Possibilistic C-Means Algorithm?, International Journal of Scientific Research in Computer Science and Engineering, Vol.6, Issue.2, pp.57-63, 2018.