Please use this identifier to cite or link to this item: http://dspace.univ-temouchent.edu.dz/handle/123456789/5875
Title: Développement d’un système de reconnaissance automatique des chiffres manuscrits isolé
Authors: MAROC, Zahira
BERRAKEM, Fatima Zahra
Keywords: Intelligence Artificielle (IA), Reconnaissance automatique des chiffres manuscrits, Réseaux de Neurones Convolutives (CNNs), Apprentissage en profondeur, apprentissage automatique, rembourrage (Padding), Tensorflow, Flask.
Artificial Intelligence (AI), Automatic recognition of handwritten digits, Convolutional Neural Networks (CNNs), Deep learning, Machine learning, Padding, Tensorflow, Flask.
Issue Date: 2023
Abstract: The recognition of handwritten digits has been a key problem in the field of handwriting recognition and machine learning for more than three decades. The use of artificial intelligence techniques and deep learning makes it possible to develop handwritten digit recognition systems capable of classifying and accurately identifying digits written by different people. The objective of our work is to set up an automatic recognition system for isolated handwritten ciphers using deep learning based on the convolutional neural network (CNN) model in order to recognize images from the MNIST database. After having trained and validated the CNN model on the preprocessed dataset, we evaluated the performance and capabilities of our system by testing it on a sample of test data. We achieved better results, achieving approximately 99.39% accuracy with a negligible error rate.
URI: http://dspace.univ-temouchent.edu.dz/handle/123456789/5875
Appears in Collections:Informatique

Files in This Item:
File Description SizeFormat 
rapport-Zahira-Maroc2023.pdf5,84 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.