Recognition of isolated handwritten Arabic characters

• Main Authors: Almansari, Osamah Abdulrahman, Nik Hashim, Nik Nur Wahidah
• Format: Conference or Workshop Item
• Language: English; English; English
• Published: Institute of Electrical and Electronics Engineers Inc. 2019
• Subjects: T Technology (General); TA Engineering (General). Civil engineering (General)
• Online Access: http://irep.iium.edu.my/79643/1/79643_Recognition%20of%20Isolated%20Handwritten_complete.pdf; http://irep.iium.edu.my/79643/7/79643_Recognition%20of%20Isolated%20Handwritten_conf..pdf; http://irep.iium.edu.my/79643/8/79643_Recognition%20of%20Isolated%20Handwritten_wos.pdf; http://irep.iium.edu.my/79643/; https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1300954
• Institution: Universiti Islam Antarabangsa Malaysia

The challenges that face the handwritten Arabic recognition are overwhelming such as different varieties of handwriting and few public databases available. Also, teaching the non-Arabic speaker at the young age is very difficult due to the unfamiliarity of the words and meanings. So, this project is focused on building a model of a deep learning architecture with convolutional neural network (CNN) and multilayer perceptron (MLP) neural network by using python programming language. This project analyzes the performance of a public database which is Arabic Handwritten Characters Dataset (AHCD). However, training this database with CNN model has achieved a test accuracy of 95.27% while training it with MLP model achieved 72.08%. Therefore, the CNN model is suitable to be used in the application device.