CNN for Handwritten Arabic Digits Recognition Based on LeNet-5

Arabic handwritten digits recognition (AHDR) is one of the most challenging convolutional neural networks (CNN) applications due to the difficult nature of Arabic digits and similarity of Arabic digits with other symbols in other languages. In this research paper, we will introduce a new technique for AHDR using CNN and entropy function as an object function. our technique introduced minimum error rate and maximum accuracy compared to other techniques.

2020

Handwritten Arabic, like other handwritten (such as Latin, Chinese, etc.), have received increasing attention from several researchers. To preserve and promote wider access to the invaluable cultural and literary heritage held in both public and private collections of manuscripts, the researchers have proposed and developed several approaches based on annotation, metadata, and transcription. The need to access to the manuscript text is increasing on a large scale. For this reason, traditional methods of indexing such as annotation or transcription will be outdated as they require a considerable and unreliable manual effort. It is, therefore, necessary to develop new tools for the identification and recognition of handwritten text contained in images. However, despite the development that has been shown by Convolutional Neural Network (CNN) in different computer vision tasks, the latter has not known many uses in the field of Arabic manuscripts. Even if, the use of these methods based on deep learning to predict the class of characters, such as the Handwritten numbers, has achieved a great result. Hence, the idea of using methods based on deep learning techniques to classify words and characters in images of Arabic manuscripts. In this paper, we propose two classification methods to predict the class of each word, using the HADARA80P dataset. The first one uses a simple neural network and the last one uses a convolutional neural network. The experimental results obtained by these two methods are very interesting

Neural Computing and Applications, 2020

Automatic handwriting recognition is an important component for many applications in various fields. It is a challenging problem that has received a lot of attention in the past three decades. Research has focused on the recognition of Latin languages’ handwriting. Fewer studies have been done for the Arabic language. In this paper, we present a new dataset of Arabic letters written exclusively by children aged 7–12 which we call Hijja. Our dataset contains 47,434 characters written by 591 participants. In addition, we propose an automatic handwriting recognition model based on convolutional neural networks (CNN). We train our model on Hijja, as well as the Arabic Handwritten Character Dataset (AHCD) dataset. Results show that our model’s performance is promising, achieving accuracies of 97% and 88% on the AHCD dataset and the Hijja dataset, respectively, outperforming other models in the literature.

Indonesian Journal of Electrical Engineering and Computer Science, 2021

Handwritten digits recognition has attracted the attention of researchers in pattern recognition fields, due to its importance in many applications in public real life, such as read bank checks and formal documents which is a continuous challenge in the last years. For this motivation, the researchers created several algorithms in recognition of different human languages, but the problem of the Arabic language is still widespread. Concerning its importance in many Arab and Islamic countries, because the people of these countries speak this language, However, there is still a little work to recognize patterns of letters and digits. In this paper, a new method is proposed that used pre-trained convolutional neural networks with resnet-34 model what is known as transfer learning for recognizing digits in the arabic language that provides us a high accuracy when this type of network is applied. This work uses a famous arabic handwritten digits dataset that called MADBase that contains 60000 training and 1000 testing samples that in later steps was converted to grayscale samples for convenient handling during the training process. This proposed method recorded the highest accuracy compared to previous methods, which is 99.6%.

Computational Intelligence and Neuroscience, 2022

Handwritten characters recognition is a challenging research topic. A lot of works have been present to recognize letters of different languages. The availability of Arabic handwritten characters databases is limited. Motivated by this topic of research, we propose a convolution neural network for the classification of Arabic handwritten letters. Also, seven optimization algorithms are performed, and the best algorithm is reported. Faced with few available Arabic handwritten datasets, various data augmentation techniques are implemented to improve the robustness needed for the convolution neural network model. The proposed model is improved by using the dropout regularization method to avoid data overfitting problems. Moreover, suitable change is presented in the choice of optimization algorithms and data augmentation approaches to achieve a good performance. The model has been trained on two Arabic handwritten characters datasets AHCD and Hijja. The proposed algorithm achieved high...

Indonesian Journal of Electrical Engineering and Computer Science

A new method for recognizing automatically Arabic handwritten words was presented using convolutional neural network architecture. The proposed method is based on global approaches, which consists of recognizing all the words without segmenting into the characters in order to recognize them separately. Convolutional neural network (CNN) is a particular supervised type of neural network based on multilayer principle; our method needs a big dataset of word images to obtain the best result. To optimize our system, a new database was collected from the benchmarking Arabic handwriting database using the pre-processing such as rotation transformation, which is applied on the images of the database to create new images with different features. The convolutional neural network applied on our database that contains 40320 of Arabic handwritten words (26880 images for training set and 13440 for test set). Thus, different configurations on a public benchmark database were evaluated and compared...

Information

The traditional algorithms for recognizing handwritten alphanumeric characters are dependent on hand-designed features. In recent days, deep learning techniques have brought about new breakthrough technology for pattern recognition applications, especially for handwritten recognition. However, deeper networks are needed to deliver state-of-the-art results in this area. In this paper, inspired by the success of the very deep state-of-the-art VGGNet, we propose Alphanumeric VGG net for Arabic handwritten alphanumeric character recognition. Alphanumeric VGG net is constructed by thirteen convolutional layers, two max-pooling layers, and three fully-connected layers. The proposed model is fast and reliable, which improves the classification performance. Besides, this model has also reduced the overall complexity of VGGNet. We evaluated our approach on two benchmarking databases. We have achieved very promising results, with a validation accuracy of 99.66% for the ADBase database and 97....

2022 25th International Conference on Computer and Information Technology (ICCIT)

Handwriting Recognition has been a field of great interest in the Artificial Intelligence domain. Due to its broad use cases in real life, research has been conducted widely on it. Prominent work has been done in this field focusing mainly on Latin characters. However, the domain of Arabic handwritten character recognition is still relatively unexplored. The inherent cursive nature of the Arabic characters and variations in writing styles across individuals makes the task even more challenging. We identified some probable reasons behind this and proposed a lightweight Convolutional Neural Network-based architecture for recognizing Arabic characters and digits. The proposed pipeline consists of a total of 18 layers containing four layers each for convolution, pooling, batch normalization, dropout, and finally one Global average pooling and a Dense layer. Furthermore, we thoroughly investigated the different choices of hyperparameters such as the choice of the optimizer, kernel initializer, activation function, etc. Evaluating the proposed architecture on the publicly available 'Arabic Handwritten Character Dataset (AHCD)' and 'Modified Arabic handwritten digits Database (MadBase)' datasets, the proposed model respectively achieved an accuracy of 96.93% and 99.35% which is comparable to the state-ofthe-art and makes it a suitable solution for real-life end-level applications.

International Journal of Multimedia Data Engineering and Management, 2019

In recent years, deep learning (DL) based systems have become very popular for constructing hierarchical representations from unlabeled data. Moreover, DL approaches have been shown to exceed foregoing state of the art machine learning models in various areas, by pattern recognition being one of the more important cases. This paper applies Convolutional Deep Belief Networks (CDBN) to textual image data containing Arabic handwritten script (AHS) and evaluated it on two different databases characterized by the low/high-dimension property. In addition to the benefits provided by deep networks, the system is protected against over-fitting. Experimentally, the authors demonstrated that the extracted features are effective for handwritten character recognition and show very good performance comparable to the state of the art on handwritten text recognition. Yet using Dropout, the proposed CDBN architectures achieved a promising accuracy rates of 91.55% and 98.86% when applied to IFN/ENIT ...

2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), 2017

Deep learning is a form of hierarchical learning, it consists of multiple layers of representations that gradually transform data into high level concepts. Deep learning has been providing the state of the art results for various computer vision problems. However, a typical deep leaning algorithm needs a large amount of data to train a deep model and guarantee the models ability to generalize. It is not easy to generate large labeled datasets and it is one of the main barriers to apply deep learning for many problems. Data augmentation schemes were introduced to overcome this limitation, by extending small available labeled datasets. In this work we experiment with extending a small labeled dataset of Arabic continuous subwords by an orders of magnitude. The labeled dataset, which consist of handwritten Arabic subwords is used to synthesize a large collection of labeled dataset. The synthesized subwords are based on one or multiple writing styles from the original labeled dataset. We also experiment with generating various printed forms of subwords. We include only Naskh font, as most of the Arabic historical manuscripts were written in this type of font. We train several convolutional neural networks using handwritten, printed and synthesized datasets and obtain encouraging results.