Handwritten digits recognition using convolution neural networks
Year: 2019
Type: article
Abstract: Convolution Neural Networks (CNNs) have been successfully used to solve variety of problems in computer vision and pattern recognition applications. In this paper, we explore the use of CNN to provide a model for handwritten digits recognition (HCCR). Various CNN architecture were explored with various data size to develop the minimum required data size that can produce optimal performance. We utilized the MNIST database of handwritten digits. The recognition results are promising.
Authors: Sam Pratt, Ana Cecilia Ochoa, Mamta Yadav, Alaa Sheta, Mahmoud El-Defrawy
Institution: Texas A&M University – Corpus Christi
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2994654191