Prediction of Handwritten Classification using CNN Techniques

Today’s computer vision industry makes extensive use of image recognition. A popular method of image recognition is digit recognition. The recognition of handwritten numbers is one of the most well-known difficulties in computer vision and machine learning applications. In essence, this model proposes an online approach for recognizing handwritten digits (HDR) by utilizing convolutional neural networks (CNN).As a training sample, the technique uses the MINST dataset, which contains centered 28x28 gray scale images of handwritten numbers. It has 10,000 test cases and 60,000 training examples. This paper shows the accuracy rate and loss of the model. Lastly, execute the trials using a variety of random handwritten 28x28 pixel digits.