Pakistani Currency Recognition to Assist Blind Person Based on Convolutional Neural Network

Authors

  • Muhammad Imad Department of Computing and Technology Abasyn University, Peshawar, Pakistan
  • Farhat Ullah Department of Computing and Technology, Abasyn University, Peshawar, Pakistan
  • Muhammad Abul Hassan Department of Computing and Technology, Abasyn University, Peshawar, Pakistan
  • Naimullah Department of Computing and Technology, Abasyn University, Peshawar, Pakistan

Keywords:

Pakistani Currency, CNN, Object Recognition, Support Vector Machine, Visually Impaired People.

Abstract

A visually impaired person faces many difficulties in their daily life, such as having trouble finding their ways, recognize the person and objects. One of the crucial problems is to recognize the currencies for a blind or visually impaired person. In this research article, we have proposed a system to recognize a Pakistani currency for a blind or visually impaired person based on Convolutional Neural Network (CNN) and Support Vector Machine (SVM). In the proposed system, seven different Pakistani paper currency notes (Rs.10, 20, 50, 100,500, 1000 and 5000) are used for training and testing. Experimental results show that the proposed system can recognize seven notes of Pakistan's Currency (Rs. 10, 20, 50, 100, 500, 1000, 5000) successfully with an accuracy of 96.85%.

Downloads

Download data is not yet available.
Dimensions

Published

2020-10-06

How to Cite

Imad, M. ., Ullah , F. ., Abul Hassan, M. ., & Naimullah. (2020). Pakistani Currency Recognition to Assist Blind Person Based on Convolutional Neural Network. Journal of Computer Science and Technology Studies, 2(2), 12-19. Retrieved from https://al-kindipublisher.com/index.php/jcsts/article/view/529