期刊名称:International Journal of Electrical and Computer Engineering
电子版ISSN:2088-8708
出版年度:2022
卷号:12
期号:4
页码:4164-4171
DOI:10.11591/ijece.v12i4.pp4164-4171
语种:English
出版社:Institute of Advanced Engineering and Science (IAES)
摘要:Tifinagh handwritten character recognition has been a challenging problem due to the similarity and variability of its alphabets. This paper proposes an optimized convolutional neural network (CNN) architecture for handwritten character recognition. The suggested model of CNN has a multi-layer feed-forward neural network that gets features and properties directly from the input data images. It is based on the newest deep learning open-source Keras Python library. The novelty of the model is to optimize the optical character recognition (OCR) system in order to obtain best performance results in terms of accuracy and execution time. The new optical character recognition system is tested on a customized dataset generated from the amazigh handwritten character database. Experimental results show a good accuracy of the system (99.27%) with an optimal execution time of the classification compared to the previous works.