Answers are grounded in this paper and cite their sources.
This project develops a CNN model improving digit recognition accuracy on the MNIST dataset, highlighting machine learning's utility in computer vision.
Abstract—Handwritten digit recognition has become a key area of research in the fields of computer vision,machine learning and pattern recognition. This project focuses on development of robust model for handwritten English digit recognition imple- menting CNN, a class of the deep learning algorithms particularly well-suited for image pro- cessing tasks. The model is trained and judged on the MNIST dataset, which consists of grayscale images of handwritten digits from 0 to 9. The CNN architecture employed in this project incorporates convolutional layers for the feature extraction, pooling layers for the dimension reduction and connected layers for the classification. Through extensive experimentation and hyperparameter tuning, the model achieves a high accuracy in digit recognition, demonstrating the effectiveness of CNNs in learning spatial hierarchies of features from input images. This system can be applied in areas such as postal automation, bank check processing, and digitization of handwritten forms. Index Terms—Handwritten Digit Recognition, Random Forest, SVM, Graph Neural Networks, Chain Codes, MNIST,Feature extraction, Machine Learning, CNN
No takes yet. Share an insight, caveat, or question.
P et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: