A DEEP LEARNING APPROACH TO HANDWRITTEN DIGIT RECOGNITION USING CONVOLUTION NEURAL NETWORK
International Research Journal of Modernization in Engineering Technology and Science · 2023
The goal of the project is to create a model that will be able to identify and recognize handwritten digits exactly from the image.It implements Convolutional Neural Network (CNN) to recognize and identify handwritten digits from images in the MNIST dataset.The CNN was able to achieve an accuracy of 99%, and the saved model was integrated with an interface for prediction.The paper also reviews other studies that have used deep learning algorithms for digit recognition, including Multilayer Perceptron (MLP) neural networks.The Paper highlight the importance of image recognition in computer science and artificial intelligence, particularly in the areas of sound and visual categorization, object detection, image segmentation, and object identification.The paper concludes by suggesting that future research could explore different classifiers and algorithms to improve the performance of the digit recognition system