Arabic Script Recognition Research Articles

A hybrid model for Arabic Script Recognition based on CNN-CBAM and BLSTM

A hybrid model for Arabic Script Recognition based on CNN-CBAM and BLSTM

Pengenalan Pola Tulisan Tangan Aksara Arab Menggunakan Ekstraksi Fitur Discrete Cosine Transform Dan Klasifikasi Backpropagation Artificial Neural Network

Arabic is a language that is spoken as the first or native language of more than 280 million people, most of whom live in the Middle East and North Africa. Apart from the Middle East and North Africa, Arabic is also familiar and often used in Indonesia because of the majority of Indonesia's population is Muslim and Arabic is the language of worship in Islam. The recognition of Arabic handwritten letters is one of the studies that has been done before, where the accuracy results obtained vary according to the research and methods used. This study aims to determine the accuracy resulting from the recognition of Arabic script handwriting patterns using a combination of the DCT(Discrete Cosine Transform) feature extraction method and the ANN Backpropagation classification method. The data used for this study were data from handwritten sources on A4 HVS paper using markers with categories of age from 7-13 years old and 18-23 years old with 15 respondents in each group and a total dataset image of 8400. Testing the best model model obtained on all images produces an accuracy of 80.79%, using the images of age range 17-23 years produces 87.27% accuracy, and the images of age range 7-13 produces an accuracy of 72.84%.
 Keywords: pengenalan pola, tulisan tangan, aksara, DCT, backpropagation

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

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.

Printed Arabic Script Recognition: A Survey

Optical character recognition (OCR) is essential in various real-world applications, such as digitizing learning resources to assist visually impaired people and transforming printed resources into electronic media. However, the development of OCR for printed Arabic script is a challenging task. These challenges are due to the specific characteristics of Arabic script. Therefore, different methods have been proposed for developing Arabic OCR systems, and this paper aims to provide a comprehensive review of these methods. This paper also discusses relevant issues of printed Arabic OCR including the challenges of printed Arabic script and performance evaluation. It concludes with a discussion of the current status of printed Arabic OCR, analyzing the remaining problems in the field of printed Arabic OCR and providing several directions for future research.

Experimental evaluation of Arabic OCR systems

Purpose The aim of this paper is to experimentally evaluate the effectiveness of the state-of-the-art printed Arabic text recognition systems to determine open areas for future improvements. In addition, this paper proposes a standard protocol with a set of metrics for measuring the effectiveness of Arabic optical character recognition (OCR) systems to assist researchers in comparing different Arabic OCR approaches. Design/methodology/approach This paper describes an experiment to automatically evaluate four well-known Arabic OCR systems using a set of performance metrics. The evaluation experiment is conducted on a publicly available printed Arabic dataset comprising 240 text images with a variety of resolution levels, font types, font styles and font sizes. Findings The experimental results show that the field of character recognition for printed Arabic still requires further research to reach an efficient text recognition method for Arabic script. Originality/value To the best of the authors’ knowledge, this is the first work that provides a comprehensive automated evaluation of Arabic OCR systems with respect to the characteristics of Arabic script and, in addition, proposes an evaluation methodology that can be used as a benchmark by researchers and therefore will contribute significantly to the enhancement of the field of Arabic script recognition.

Urdu Nasta'liq text recognition using implicit segmentation based on multi-dimensional long short term memory neural networks.

The recognition of Arabic script and its derivatives such as Urdu, Persian, Pashto etc. is a difficult task due to complexity of this script. Particularly, Urdu text recognition is more difficult due to its Nasta’liq writing style. Nasta’liq writing style inherits complex calligraphic nature, which presents major issues to recognition of Urdu text owing to diagonality in writing, high cursiveness, context sensitivity and overlapping of characters. Therefore, the work done for recognition of Arabic script cannot be directly applied to Urdu recognition. We present Multi-dimensional Long Short Term Memory (MDLSTM) Recurrent Neural Networks with an output layer designed for sequence labeling for recognition of printed Urdu text-lines written in the Nasta’liq writing style. Experiments show that MDLSTM attained a recognition accuracy of 98% for the unconstrained Urdu Nasta’liq printed text, which significantly outperforms the state-of-the-art techniques.

Online versus offline Arabic script classification

Arabic script classification is a complex area of research in the field of computer vision. The issue of offline Arabic script classification has been a concern of many researchers interest currently as it is assumed that online Arabic script recognition is comparatively simple and significant achievements have been attained. Numerous researchers deal with these issues evolved in pre-processing and post-processing techniques of Arabic script and presented various approaches to improve its accuracy rate. However, offline Arabic script classification and its related issues are still fresh. In this paper, we focus on pre-processing to post-processing techniques and highlight several issues in each phase in order to highlight need of high classification performance for Arabic script classification (offline and online). Additionally, top experimental results are reported, discussed and compared, and current challenges are also discussed. Finally, online versus offline Arabic script recognition achievements are also compared.

Segmentation techniques for recognition of Arabic-like scripts: A comprehensive survey

Arabic script based text recognition system has been a popular field of research for many years that can be used in the learning and teaching process to the students and educators how to read and understand educational contents of Arabic script. The challenging nature of Arabic script recognition has attracted the attention of researchers from both industry and academic circles but these efforts have not achieved good results until now. Segmentation of Urdu script when written in Nasta’liq writing style is very difficult task due to the complexity of writing style as compare to Naskh writing style. Good segmentation is one of the reasons for high accuracy. Character segmentation has been a critical phase of the OCR process. The higher recognition rates for isolated characters as compare to results of words or connected character well illustrate the importance of segmentation. Current study investigates the recent work for character segmentation and challenges for segmentation for Arabic script based languages.

SEGMENTATION-FREE ONLINE ARABIC HANDWRITING RECOGNITION

Arabic script is naturally cursive and unconstrained and, as a result, an automatic recognition of its handwriting is a challenging problem. The analysis of Arabic script is further complicated in comparison to Latin script due to obligatory dots/stokes that are placed above or below most letters. In this paper, we introduce a new approach that performs online Arabic word recognition on a continuous word-part level, while performing training on the letter level. In addition, we appropriately handle delayed strokes by first detecting them and then integrating them into the word-part body. Our current implementation is based on Hidden Markov Models (HMM) and correctly handles most of the Arabic script recognition difficulties. We have tested our implementation using various dictionaries and multiple writers and have achieved encouraging results for both writer-dependent and writer-independent recognition.

On-line Arabic handwriting recognition with templates

After a long period of focus on western and East Asian scripts there is now a general trend in the on-line handwriting recognition community to explore recognition of other scripts such as Arabic and various Indic scripts. One difficulty with the Arabic script is the number and position of diacritic marks associated to Arabic characters. This paper explores the application of a template matching scheme to the recognition of Arabic script with a novel algorithm for dynamically treating the diacritical marks. Template based systems are robust to conditions with scarce training data and in experiments the proposed system outperformed a reference system based on the promising state-of-the-art network technique of BLSTM. Experiments have been conducted in an environment similar to that of many handheld devices with promising results both in terms of memory consumption and response time.

A heuristic algorithm for optical character recognition of Arabic script

In this paper, a heuristic method is developed for segmentation, feature extraction and recognition of the Arabic script. The study is part of a large project for transcription of the documents in Ottoman Archives. A geometrical and topological feature analysis method is developed for segmentation and feature extraction stages. Chain code transformation is applied to main strokes of the characters, which are classified by the hidden Markov model (HMM) in the recognition stage. Experimental results indicate that the performance of the proposed method is quite satisfactory, provided that the thinning process does not yield spurious branches.