计算机工程与信息技术学报

Handwritten Digit Recognition

Shubhangi* and Ravi Shankar Pandey

Handwritten Digit Recognition (HDR) is the process of converting images of handwritten digit into digital format. A lot of money is wasted on converting the information that is in paper to digital format. This problem can be solved by using HDR. The heart of our project lies within the ability to develop an efficient algorithm that can recognize the handwritten digits which are scanned and sent as input by the user. The goal of this paper is to observe the variation of different algorithms that can classify the handwritten digits using different hidden layers, various numbers of epochs and to make a comparison based on the accuracy. This experiment is performed using the Modified National Institute of Standards and Technology (MNIST) dataset.