The project aims to identify the handwritten digits taken from the MNIST dataset using the KNN algorithm. The handwritten digit recognition is the ability of computers to recognize human handwritten digits. It is a hard task for the machine because handwritten digits are not perfect and can be made with many different flavors. So, the machine trains itself for recognizing the digits from different sources like emails, bank cheque, papers, images, etc. and in different real-world scenarios as well. The model have been trained on MNIST dataset of 42000 values. The images of handwritten digits are shown as a matrix of 28×28 where every cell consists of a grayscale pixel value varying from 0 to 9. The accuracy obtained for the KNN model is 96.3%.