KNN and the CNN for Handwritten Digit Recognition: A comparative study

The automatic identification of handwritten digits by computers or other devices is referred to as "handwritten digit recognition technology,"and it has a wider range of potential applications in the processing of bank bills, financial statements, and postage stamps. This study examines the methods KNN, and CNN, and their use in handwritten digit recognition using samples from the MNIST handwritten digit database. In order to achieve the best results for each method, this work rewrites KNN with Python and CNN with Tensorflow throughout the training phase. The benefits and drawbacks of the two AI based techniques employed for handwriting recognition the results has been in terms of recognition rate. © 2023 IEEE.