Revolutionizing digit image recognition: pushing the limits with simple CNN and challenging image augmentation techniques on MNIST

• Main Authors: Hulliyah, Khodijah, Awang Abu Bakar, Normi Sham, Aripiyanto, Saepul, Khairani, Dewi
• Format: Article
• Language: English; English
• Published: Bright Publisher 2023
• Subjects: T10.5 Communication of technical information
• Online Access: http://irep.iium.edu.my/107246/1/107246_Revolutionizing%20digit%20image%20recognition.pdf; http://irep.iium.edu.my/107246/2/107246_Revolutionizing%20digit%20image%20recognition_SCOPUS.pdf; http://irep.iium.edu.my/107246/; https://bright-journal.org/Journal/index.php/JADS/article/view/104
• Institution: Universiti Islam Antarabangsa Malaysia

This study aims to apply Convolutional Neural Networks (CNN) and image augmentation techniques in digit recognition using the MNIST dataset. We built a CNN model and experimented with various image augmentation techniques to improve digit recognition accuracy. The results showed that the use of CN...