Arabic Online Handwriting Recognition Using Neural Network

Mars, Abdelkarim; Antoniadis, Georges

doi:10.5121/ijaia.2016.7504

Cited by 9 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mars A, Antoniadis G (2016) [10] created an Arabic database with "6090-Characters" and "1080-Words" for word and character recognition. The classification was done by employing a "Neural Network" and a "Time-Delay Neural Network (TDNN)".…”

Section: Related Workmentioning

confidence: 99%

OCR for Arabic character recognition with advanced principal component analysis based on feature extraction and fuzzy-KNN based classification

Fredrik

2022

ijhs

View full text Add to dashboard Cite

Offline character recognition has become a highly important study field for various pattern recognition applications in recent years. Several handwritten character recognition systems have been suggested, with the complexity of these systems varying depending on the recognizing units' writing styles. In reality, identifying letters or numerals is far simpler than recognizing cursive sentences or lines of text. As a result, early handwriting recognition algorithms could only distinguish a few characters with limited vocabularies. Nowadays Arabic handwritten character recognition is very important as it is very difficult to identify. The cursive writing and variety of styles make this recognition more complex. This paper presents an automated model for ACR. This ACR is constructed from four phases: Preprocessing, Segmentation, Feature Extraction, and Classification. In this research article, we compare the advanced EPSO EKNN Algorithm with the earlier DBN Algorithm and also suggest a new method having higher Accuracy. In this research article, the "Enhanced K-Nearest Neighbor" (EKNN) classification model was used to identify and classify or simply recognize the particular Arabic character, and the "Extended Particle Swarm Optimization" (EPSO) methodology was introduced to select the best feature from feature extraction to comply with Arabic-Character Classification.

show abstract

Section: Related Workmentioning

confidence: 99%

OCR for Arabic character recognition with advanced principal component analysis based on feature extraction and fuzzy-KNN based classification

Fredrik

2022

ijhs

View full text Add to dashboard Cite

show abstract

“…Selain menggunakan CNN ada juga penelitian yang menggunakan metode Multi Layer Perceptron (MLP) seperti yang dilakukan oleh Ashiquzzaman et al [12] pada tahun 2017 dengan akurasi sebesar 93,8% dan Das et al [13] pada tahun 2006 dengan akurasi sebesar 94,93%. Tak hanya CNN dan MLP juga ada penelitian yang menggunakan metode Time Delay Neural Network (TDNN) yang dilakukan oleh Mars et al [14] pada tahun 2016 dengan akurasi sebesar 98,5%.…”

Section: Pendahuluanunclassified

Pengenalan Tulisan Tangan Huruf Hijaiyah Menggunakan Convolution Neural Network Dengan Augmentasi Data

Pradika

Nugroho

Puspaningrum

2020

santika

View full text Add to dashboard Cite

Sistem pengenalan tulisan tangan huruf hijaiyah diperlukan untuk melakukan koreksi otomatis terhadap seseorang yang tengah belajar menulisnya. Dalam pengimplementasiannya terdapat beberapa tantangan. Tantangan seperti banyaknya bentuk variasi tulisan tangan huruf hijaiyah, pemilihan arsitektur yang tepat, dan banyak data pelatihan yang dibutuhkan agar sistem dapat memprediksi secara akurat. Convolutional Neural Network (CNN) adalah salah satu algoritma deep learning yang efektif dalam mengolah citra yang dapat dilatih baik secara supervised learning maupun unsupervised learning. Model CNN dilatih menggunakan dataset Hijaiyah1SKFI. Dataset tersebut terdiri dari 2100 data dengan 30 kelas yakni huruf alif hingga ya yang ditulis oleh 4 orang berbeda dengan 80% digunakan sebagai data latih dan 20% adalah data tes. Dalam makalah ini dilakukan optimisasi berupa augmentasi data karena data yang tidak banyak sehingga dengan data yang sedikit maka variasi data pelatihan akan bertambah. Arsitektur yang diusung di makalah ini bernama SIP-Net mendapatkan akurasi pada data uji sebesar 99.7%.

show abstract

“…In [27] presented a model for Optical Character Recognition (OCR) in Telugu language, which includes three parts: a database of Telugu characters, a deep learning-based OCR algorithm and an online client-server application for the developed algorithm. Their model based on Convolutional Neural Networks (CNNs) algorithm reasonably to classify the characters.…”

Section: Related Work On Convolutonal Neural Network Techniquesmentioning

confidence: 99%

A Review of Arabic Optical Character Recognition Techniques & Performance

Alwaqfi¹,

Mohamad²

2020

IJETT

View full text Add to dashboard Cite

The Artificial intelligence one of the most perspective and interesting research area that takes attention from many researchers. Several studies focused the interest in Optical Character Recognition, which is computer software designed for converting images with text into machine processed text. These OCR systems available for several languages including Arabic, Arabic OCR has been developed and improved over decades, which ultimately causes to a huge number quantity of approaches with robust results with high, in some cases about 99%, while using deep learning in Arabic OCR can results up to 100% accuracy with short time and less resources to process the image. The characteristics of Arabic text cause more errors than in English text in OCR. The aim of this paper is to analyze the related works and issues in Arabic language OCRs. The analysis results show that existing OCRs within implementation with other application exhibit defects, or at least just their subsets, such as low-resolution inputs and video-based inputs. Accordingly, it is necessary to review existing approaches that have reliable results. In addition, the review of deep learning for Arabic OCR systems and researches is very important and useful. This paper presents a literature review on the existing systems Arabic text recognition, consists of a typical mechanism, lists the differences, advantages, and disadvantages that help in adopting or expanding these systems in accordance with modern requirements.

show abstract

Arabic Online Handwriting Recognition Using Neural Network

Abstract: ABSTRACT

Cited by 9 publications

References 10 publications

OCR for Arabic character recognition with advanced principal component analysis based on feature extraction and fuzzy-KNN based classification

OCR for Arabic character recognition with advanced principal component analysis based on feature extraction and fuzzy-KNN based classification

Pengenalan Tulisan Tangan Huruf Hijaiyah Menggunakan Convolution Neural Network Dengan Augmentasi Data

A Review of Arabic Optical Character Recognition Techniques & Performance

Contact Info

Product

Resources

About