Author Login IJIRT Partner Network (IPN) Login

Handwritten Digit Recognition Using CNN - A Transfer Learning Approach

  • Unique Paper ID: 174649
  • Volume: 11
  • Issue: 11
  • PageNo: 866-868
  • Abstract:
  • Handwritten digit recognition is an essential task in computer vision, widely used in banking, postal services, and automated document processing. This paper presents an advanced Convolutional Neural Network (CNN) architecture with Transfer Learning to enhance recognition accuracy while reducing computational costs. The model is trained on MNIST and EMNIST datasets, employing data augmentation, dropout regularization, and hyperparameter tuning to optimize performance. The proposed system achieves an accuracy of 99.2% on MNIST and 97.8% on EMNIST using a hybrid approach. Experimental results demonstrate improved robustness compared to conventional CNN models [1][2].
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 11
  • PageNo: 866-868

Handwritten Digit Recognition Using CNN - A Transfer Learning Approach

Related Articles

Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry