A Convolutional Neural Network for Handwritten Digit Recognition
Cristina Guevara Neri, Osslan Osíris Vergara Villegas, Vianey Guadalupe Cruz Sánchez, Manuel Nandayapa, Humberto Sossa · International Journal of Combinatorial Optimization Problems and Informatics. · 2020
Technological development in recent years has generated the constant need to digitalize and analyze data, where handwritten digit recognition is a popular problem. This paper focuses on the creation of two handwritten digit datasets and their use to train a Convolutional Neural Network (CNN) to classify them, also, a proposed extra preprocessing technique is applied to the images of one of the data sets. Experiments show that the proposed preprocessing technique lead to obtain accuracies above 98%, which were higher than the values obtained with the dataset without the additional preprocessing.