Optimised CNN Architectures for Handwritten Arabic Character Recognition
Open Access
- 1 January 2024
- journal article
- research article
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 79 (3) , 4905-4924
Abstract
Handwritten character recognition is considered challenging compared with machine-printed characters due to the different human writing styles. Arabic is morphologically rich, and its characters have a high similarity. The Arabic language includes 28 characters. Each character has up to four shapes according to its location in the word (at the beginning, middle, end, and isolated). This paper proposed 12 CNN architectures for recognizing handwritten Arabic characters. The proposed architectures were derived from the popular CNN architectures, such as VGG, ResNet, and Inception, to make them applicable to recognizing character-size images. The experimental results on three well-known datasets showed that the proposed architectures significantly enhanced the recognition rate compared to the baseline models. The experiments showed that data augmentation improved the models’ accuracies on all tested datasets. The proposed model outperformed most of the existing approaches. The best achieved results were 93.05%, 98.30%, and 96.88% on the HIJJA, AHCD, and AIA9K datasets.Keywords
This publication has 33 references indexed in Scilit:
- Hybrid Arabic handwritten character segmentation using CNN and graph theory algorithmJournal of King Saud University Computer and Information Sciences, 2024
- OCR-MRD: performance analysis of different optical character recognition engines for medical report digitizationInternational Journal of Information Technology, 2023
- Automated player identification and indexing using two-stage deep learning networkScientific Reports, 2023
- Automatic imagery Bank Cheque data extraction based on machine learning approaches: a comprehensive surveyMultimedia Tools and Applications, 2023
- Recognizing arabic handwritten characters using deep learning and genetic algorithmsMultimedia Tools and Applications, 2021
- A new Arabic handwritten character recognition deep learning system (AHCR-DLS)Neural Computing and Applications, 2020
- Arabic handwriting recognition system using convolutional neural networkNeural Computing and Applications, 2020
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998