scholarly journals Deep ensemble neural networks for recognizing isolated Arabic handwritten characters

2020 ◽  
Vol 6 (21) ◽  
pp. 68-79
Author(s):  
Haifa Alyahya ◽  
Mohamed Maher Ben Ismail ◽  
AbdulMalik Al-Salman
Keyword(s):  
Character Recognition ◽  
Research Field ◽  
Ensemble Model ◽  
Standard Arabic ◽  
Handwritten Character ◽  
Arabic Characters ◽  
Ensemble Neural Networks ◽  
Active Research ◽  
Fully Connected ◽  
Handwritten Arabic

In recent years, handwritten character recognition has become an active research field. In particular, digitalization has triggered the interest of researchers from various computing disciplines to address several handwriting related challenges. Despite these efforts, there are still opportunities for the development and improvement of the recognition of the handwritten Arabic letters. In this paper, we designed and developed a deep ensemble architecture in which ResNet-18 architecture is exploited to model and classify character images. Specifically, we adapted ResNet-18 by adding a dropout layer after all convolutional layer and integrated it in multiple ensemble models to automatically recognize isolated handwritten Arabic characters. A standard Arabic Handwritten Character Dataset (AHCD) was used in the experiments to train and assess all the proposed models. Satisfactory results were obtained using all models. The best-attained accuracy was 98.30% using a typical ResNet-18 model. Similarly, 98.00% and 98.03% accuracies were obtained using an ensemble model with one fully connected layer (1 FC) and an ensemble with two fully connected layers (2 FC) coupled with a dropout layer, respectively.

scholarly journals A Survey on Arabic Handwritten Script Recognition Systems

2021 ◽  
Vol 11 (2) ◽  
pp. 1-17
Author(s):  
Soumia Djaghbellou ◽  
Abderraouf Bouziane ◽  
Abdelouahab Attia ◽  
Zahid Akhtar
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Research Field ◽  
Research Directions ◽  
Optical Character ◽  
On Line ◽  
Recognition Systems ◽  
Active Research ◽  
Handwritten Arabic ◽  
Open Issues

The optical character recognition (OCR) system is still an active research field in pattern recognition. Such systems can identify, recognize and distinguish electronically between characters and texts, printed or handwritten. They can also do a transformation of such data type into machine-processable form to facilitate the interaction between user and machine in various applications. In this paper, we present the global structure of an OCR system, with its types (on-line and off-line), categories (printed and handwritten) and its main steps. We also focused on off-line handwritten Arabic character recognition and provided a list of the main datasets publicly available. This paper also presents a survey of the works that have been carried out over recent years. Finally, some open issues and potential research directions have been highlighted

scholarly journals A Survey on Arabic Handwritten Script Recognition Systems

2021 ◽  
Vol 11 (2) ◽  
pp. 0-0
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Research Field ◽  
Research Directions ◽  
Optical Character ◽  
On Line ◽  
Recognition Systems ◽  
Active Research ◽  
Handwritten Arabic ◽  
Open Issues

The optical character recognition (OCR) system is still an active research field in pattern recognition. Such systems can identify, recognize and distinguish electronically between characters and texts, printed or handwritten. They can also do a transformation of such data type into machine-processable form to facilitate the interaction between user and machine in various applications. In this paper, we present the global structure of an OCR system, with its types (on-line and off-line), categories (printed and handwritten) and its main steps. We also focused on off-line handwritten Arabic character recognition and provided a list of the main datasets publicly available. This paper also presents a survey of the works that have been carried out over recent years. Finally, some open issues and potential research directions have been highlighted

scholarly journals Offline Handwritten Character Recognition using Convolutional Neural Network

2021 ◽  
Vol 9 (8) ◽  
pp. 1483-1489
Author(s):  
N. Devi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Character Recognition ◽  
Recognition Accuracy ◽  
Probability Score ◽  
Convolution Operation ◽  
Handwritten Character ◽  
Handwritten Text ◽  
Proposed Model ◽  
Fully Connected

Abstract: This paper focuses on the task of recognizing handwritten Hindi characters using a Convolutional Neural Network (CNN) based. The recognized characters can then be stored digitally in the computer or used for other purposes. The dataset used is obtained from the UC Irvine Machine Learning Repository which contains 92,000 images divided into training (80%) and test set (20%). It contains different forms of handwritten Devanagari characters written by different individuals which can be used to train and test handwritten text recognizers. It contains four CNN layers followed by three fully connected layers for recognition. Grayscale handwritten character images are used as input. Filters are applied on the images to extract different features at each layer. This is done by the Convolution operation. The two other main operations involved are Pooling and Flattening. The output of the CNN layers is fed to the fully connected layers. Finally, the chance or probability score of each character is determined and the character with the highest probability score is shown as the output. A recognition accuracy of 98.94% is obtained. Similar models exist for the purpose, but the proposed model achieved a better performance and accuracy than some of the earlier models. Keywords: Devanagari characters, Convolutional Neural Networks, Image Processing

scholarly journals Full depth CNN classifier for handwritten and license plate characters recognition

2021 ◽  
Vol 7 ◽  
pp. e576
Author(s):  
Mohammed Salemdeeb ◽  
Sarp Ertürk
Keyword(s):  
United Arab Emirates ◽  
Character Recognition ◽  
State Of The Art ◽  
Low Complexity ◽  
Research Field ◽  
License Plate ◽  
Important Research ◽  
Kingdom Of Saudi Arabia ◽  
Fully Connected ◽  
Low Complex

Character recognition is an important research field of interest for many applications. In recent years, deep learning has made breakthroughs in image classification, especially for character recognition. However, convolutional neural networks (CNN) still deliver state-of-the-art results in this area. Motivated by the success of CNNs, this paper proposes a simple novel full depth stacked CNN architecture for Latin and Arabic handwritten alphanumeric characters that is also utilized for license plate (LP) characters recognition. The proposed architecture is constructed by four convolutional layers, two max-pooling layers, and one fully connected layer. This architecture is low-complex, fast, reliable and achieves very promising classification accuracy that may move the field forward in terms of low complexity, high accuracy and full feature extraction. The proposed approach is tested on four benchmarks for handwritten character datasets, Fashion-MNIST dataset, public LP character datasets and a newly introduced real LP isolated character dataset. The proposed approach tests report an error of only 0.28% for MNIST, 0.34% for MAHDB, 1.45% for AHCD, 3.81% for AIA9K, 5.00% for Fashion-MNIST, 0.26% for Saudi license plate character and 0.97% for Latin license plate characters datasets. The license plate characters include license plates from Turkey (TR), Europe (EU), USA, United Arab Emirates (UAE) and Kingdom of Saudi Arabia (KSA).

AN ANALYTICAL STUDY OF HANDWRITTEN CHARACTER RECOGNITION

2016 ◽  
Vol 2 (4) ◽  
pp. 26
Author(s):  
VOHRA UJWAL SINGH ◽  
DWIVEDI SHRI PRAKASH ◽  
MANDORIA H.L ◽  
◽  
◽  
...  
Keyword(s):  
Character Recognition ◽  
Analytical Study ◽  
Handwritten Character Recognition ◽  
Handwritten Character

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Sign in / Sign up

Export Citation Format

Share Document