We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Recognizing arabic handwritten characters using deep learning and genetic algorithms.
- Authors
Balaha, Hossam Magdy; Ali, Hesham Arafat; Youssef, Esraa Khaled; Elsayed, Asmaa Elsayed; Samak, Reem Adel; Abdelhaleem, Mohammed Samy; Tolba, Mohammed Mosa; Shehata, Mahmoud Ragab; Mahmoud, Mahmoud Refa'at; Abdelhameed, Mariam Mahmoud; Mohammed, Mostafa Mahmoud
- Abstract
Automated techniques for Arabic content recognition are at a beginning period contrasted with their partners for the Latin and Chinese contents recognition. There is a bulk of handwritten Arabic archives available in libraries, data centers, historical centers, and workplaces. Digitization of these documents facilitates (1) to preserve and transfer the country's history electronically, (2) to save the physical storage space, (3) to proper handling of the documents, and (4) to enhance the retrieval of information through the Internet and other mediums. Arabic handwritten character recognition (AHCR) systems face several challenges including the unlimited variations in human handwriting and the leakage of large and public databases. In the current study, the segmentation and recognition phases are addressed. The text segmentation challenges and a set of solutions for each challenge are presented. The convolutional neural network (CNN), deep learning approach, is used in the recognition phase. The usage of CNN leads to significant improvements across different machine learning classification algorithms. It facilitates the automatic feature extraction of images. 14 different native CNN architectures are proposed after a set of try-and-error trials. They are trained and tested on the HMBD database that contains 54,115 of the handwritten Arabic characters. Experiments are performed on the native CNN architectures and the best-reported testing accuracy is 91.96%. A transfer learning (TF) and genetic algorithm (GA) approach named "HMB-AHCR-DLGA" is suggested to optimize the training parameters and hyperparameters in the recognition phase. The pre-trained CNN models (VGG16, VGG19, and MobileNetV2) are used in the later approach. Five optimization experiments are performed and the best combinations are reported. The highest reported testing accuracy is 92.88%.
- Subjects
MACHINE learning; GENETIC algorithms; PATTERN recognition systems; DEEP learning; CONVOLUTIONAL neural networks; CLASSIFICATION algorithms
- Publication
Multimedia Tools & Applications, 2021, Vol 80, Issue 21-23, p32473
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-021-11185-4