Optical Character Recognition of Arabic handwritten characters using Neural Network

Hussien, Rana S.; Elkhidir, Azza A.; Elnourani, Mohamed

doi:10.1109/iccneee.2015.7381412

Cited by 19 publications

(14 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the work in [9] is limited to optical character recognition of Nastaliq fonts only. Hussain et al, proposed an offline OCR system to recognize only eight Arabic handwritten characters with accuracy rate of 77.25% [10]. The framework proposed by Elenwar et al, [11] used Arabic characters database containing 1814 characters for training and 435 characters for testing.…”

Section: Literature Reviewmentioning

confidence: 99%

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

et al. 2020

View full text Add to dashboard Cite

Automatic recognition of Urdu handwritten digits and characters, is a challenging task. It has applications in postal address reading, bank's cheque processing, and digitization and preservation of handwritten manuscripts from old ages. While there exists a significant work for automatic recognition of handwritten English characters and other major languages of the world, the work done for Urdu language is extremely insufficient. This paper has two goals. Firstly, we introduce a pioneer dataset for handwritten digits and characters of Urdu, containing samples from more than 900 individuals. Secondly, we report results for automatic recognition of handwritten digits and characters as achieved by using deep auto-encoder network and convolutional neural network. More specifically, we use a two-layer and a three-layer deep autoencoder network and convolutional neural network and evaluate the two frameworks in terms of recognition accuracy. The proposed framework of deep autoencoder can successfully recognize digits and characters with an accuracy of 97% for digits only, 81% for characters only and 82% for both digits and characters simultaneously. In comparison, the framework of convolutional neural network has accuracy of 96.7% for digits only, 86.5% for characters only and 82.7% for both digits and characters simultaneously. These frameworks can serve as baselines for future research on Urdu handwritten text.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The OCR General Structural [6] OCR in Arabic language is very difficult process, because the letters in Arabic language are connected without spaces in the same word, and their shape is changed in dependence of characters position in the words [4]. There are several factors effect positive or negative with the accuracy for the OCR results, like cursive written-based languages [7], low resolution scanning image [8], and the noise of image [9].…”

Section: Related Workmentioning

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

“…2) Initialize the neural network training after size normalization and noise removal. B. Rana S. Hussien [2] gives the Optical Character Recognition (OCR) by using Artificial Neural Networks (ANNs) classifiers.…”

Section: Literature Survey a Suman Avdhesh Yadav Proposed A Systmentioning

confidence: 99%

Review of methods for Handwritten Character Identification using Optical Character Recognition (OCR)

Gurav¹

2019

IJRASET

View full text Add to dashboard Cite

It is very hard to recognize handwritten character using optical character recognition. Also it is very difficult to convert handwritten image into text format. Optical character recognition has become one of the most successful applications of technology in the field of pattern recognition and artificial intelligence. OCR is a widespread technology to recognize text inside images, such as scanned documents and photos. This paper gives the survey of different techniques used by the researcher for dynamic pattern and character recognition.

show abstract

Optical Character Recognition of Arabic handwritten characters using Neural Network

Cited by 19 publications

References 2 publications

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

A Review of Arabic Optical Character Recognition Techniques & Performance

Review of methods for Handwritten Character Identification using Optical Character Recognition (OCR)

Contact Info

Product

Resources

About