MNIST and SVHN Digit Classification

Chandrakala, S. and Ghani, Mariam and Sanath, B S and Murugan, Swathika (2025) MNIST and SVHN Digit Classification. International Journal of Science and Research Archive, 16 (1). pp. 1919-1923. ISSN 2582-8185

By utilising the MNIST database coupled with the SVHN data, identification of multiple handwritten digits is being achieved by the model built. In this particular use case, Convolutional neural networks (CNN) algorithm is integrated with the MNIST dataset, whereas Long short-term memory (LSTM) is employed for the SVHN dataset to sequentially classify the digits. Furthermore, the concatenation of both outputs will be trained using a final classifier. The MNIST database contains numbers ranging from 0-9, while the other database is similar in flavour, containing over 60,000 labelled images. The primary goal of this project is to develop a reliable, effective, and efficient methodology for recognizing and identifying multiple handwritten digits with minimum errors. The applications of such an accurate model lies in banking sectors, healthcare departments and many more.