Handwritten Digit Recognition System using Convolutional Neural Network (CNN)


  • KIAT YONG GOH 0166893767
  • Aimi Syammi Binti Ab Ghafar


Handwritten Digit Recognition, Machine Learning, MNIST Dataset, Convolutional Neural Network


One of the technically important problems in pattern recognition systems is the handwritten digit recognition. The digit recognition applications include postal mail sorting, bank check processing, data entry forms, etc. The basic purpose of the study was to develop an algorithm based on machine learning and develop an optimization technique to increase the accuracy of handwritten digits recognition, and to analyse the performance of the proposed algorithm with test data set. There are several machine learning algorithms such as Support Vector Machine, Random Forest, Multilayer Perceptron, Convolutional Neural Network etc. In this project is aimed to use Convolutional Neural Network to complete the task. The MNIST dataset also used in this project. Even though the goal of the project is creating a model to recognize digits, it can be extended for letters in future work with the same concept. The result shows the accuracy of the model is 98% and above after evaluated the model, it was a good result compare other algorithms. Model improvement is done by increasing the depth of the model. The performance of updated version model has a small improvement of accuracy from 98.655% to 98.962%.




How to Cite

GOH, K. Y., & Binti Ab Ghafar, A. S. . (2021). Handwritten Digit Recognition System using Convolutional Neural Network (CNN). Progress in Engineering Application and Technology, 2(1), 578–592. Retrieved from https://publisher.uthm.edu.my/periodicals/index.php/peat/article/view/960