MNIST Kannada Digit Recognition

Authors

  • P. G. Shwetha Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • Prajna Gatty Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • Shubhashini Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • B. Shraddha Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • K. Janardhana Bhat Assistant Professor, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India

Keywords:

Computer Vision, Convolutional Neural Network (CNN), Dig MNSIT, Handwritten digit recognition, K-Nearest Neighbor (KNN), Kannada-MNIST, Pattern Recognition, Random Forest Classifier (RFC), Support Vector Machine (SVM)

Abstract

Handwritten digit recognition, an active research field of computer vision and pattern recognition. This paper proposes an efficient handwritten Kannada digit recognition approach based on comparing the prediction accuracy of the Convolutional Neural Network (CNN) model and various machine learning algorithms such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Random Forest Classifier (RFC) by training on Kannada-MNIST and testing on the Dig MNIST dataset. The Kannada language has complex digits, identifying such digits is a challenge in pattern recognition. In the end, a comparative study of the above-mentioned algorithms is performed based on recognition accuracy.

Downloads

Download data is not yet available.

Downloads

Published

2021-07-22

How to Cite

[1]
P. G. Shwetha, P. Gatty, Shubhashini, B. Shraddha, and K. J. Bhat, “MNIST Kannada Digit Recognition”, IJRESM, vol. 4, no. 7, pp. 247–249, Jul. 2021.

Issue

Section

Articles

Most read articles by the same author(s)