Improvement of Context Dependent Modeling for Arabic Handwriting Recognition

Hamdani, Mahdi; Doetsch, Patrick; Ney, Hermann

doi:10.1109/icfhr.2014.89

Cited by 7 publications

(3 citation statements)

References 18 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results in table shown an improvement due to the contextual character modeling: accuracy is increased by 0.6% in absolute value which corresponds to a 7.8% reduction in error rate; this shows the effectiveness of modeling overlapped characters by specific models while keeping the total number of models manageable. The proposed work by Hamdani [17] had evaluated in OpenHart database [20]; an absolute improvement of 2.9% in terms of WER (Word Error Rate) is performed by using the context dependent labels and the lossy mapping CART. Irfane [19] proposed sub-character HMM models for Arabic text recognition that allow sharing of common patterns between different position-dependent shape forms of an Arabic character as well as between different character.…”

Section: Comparative Resultsmentioning

confidence: 99%

A Survey of Contextual Handwritten Recognition Systems based HMMs for Cursive Arabic and Latin Script

Rabi¹,

Amrouch²,

Mahani³

2017

IJCA

View full text Add to dashboard Cite

Offline handwriting recognition has become lately a very popular research area and the number of its possible application is very large. Most recognition system are based on modeling characters to recognize, then the concatenation of these models to recognize a word, while modeling character allows deformations related to its context. This paper provides a survey of handwritten recognition systems based on context-dependent character modeling to account possible deformations related to its context. It examines the literature on the most significant work in contextual handwritten text recognition for two different alphabets, Latin and Arabic. Finally discussing the comparative results to achieve a comprehensive summary of the various approaches and systems taking account the character's context which could help open up some interesting new prospects.

show abstract

Section: Comparative Resultsmentioning

confidence: 99%

A Survey of Contextual Handwritten Recognition Systems based HMMs for Cursive Arabic and Latin Script

Rabi¹,

Amrouch²,

Mahani³

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Hamdani et al, in (Hamdani, Doetsch & Ney, 2014), introduced the CART trees to use it in the state tying. Taken in concentration a set of questions, those are very important in the CART tree that creation by a "loss mapping" compartmentalization for the Arabic shapes.…”

Section: Literature Reviewmentioning

confidence: 99%

Arabic Hand Written Character Recognition Based on Contour Matching and Neural Network

Zanona¹,

Abuhamdah²,

El-Zaghmouri³

2019

CIS

View full text Add to dashboard Cite

Complexity of Arabic writing language makes its handwritten recognition very complex in terms of computer algorithms. The Arabic handwritten recognition has high importance in modern applications. The contour analysis of word image can extract special contour features that discriminate one character from another by the mean of vector features. This paper implements a set of pre-processing functions over a handwritten Arabic characters, with contour analysis, to enter the contour vector to neural network to recognize it. The selection of this set of pre-processing algorithms was completed after hundreds of tests and validation. The feed forward neural network architecture was trained using many patterns regardless of the Arabic font style building a rigid recognition model. Because of the shortcomings in Arabic written databases or datasets, the testing was done by non-standard data set. The presented algorithm structure got recognition ratio about 97%.

show abstract

“…This study proposed new techniques to recognize the Arabic handwritten words and sub words, which make it valuable to document it in the research related works regardless of all its differences with the research methods and techniques. Hamdani et al (2014), introduced the CART trees to use it in the state tying. Taken in concentration a set of questions, those are very important in the CART tree that…”

Section: Literature Reviewmentioning

confidence: 99%

Isolated Arabic Hand Written Letters Recognition Based on Contour Matching and Neural Network

Aljunaeidia¹,

Alkhasawneh²,

BaniYounes³

2018

Journal of Computer Science

View full text Add to dashboard Cite

Complexity of Arabic writing language makes its handwritten recognition very complex in terms of computer algorithms comparing with other languages such as English and French. The Arabic handwritten recognition has high importance in modern applications. The contour analysis of word image can extract special contour features that discriminate one character from another by the mean of vector features. This paper aims to implements a set of pre-processing functions over a handwritten Arabic character, with contour analysis, to enter the contour vector to neural network to recognize it. For training part, the neural network architecture was trained using many patterns regardless of the Arabic font style building a rigid recognition model. The presented algorithm structure got recognition ratio about 97%.

show abstract

Improvement of Context Dependent Modeling for Arabic Handwriting Recognition

Cited by 7 publications

References 18 publications

A Survey of Contextual Handwritten Recognition Systems based HMMs for Cursive Arabic and Latin Script

A Survey of Contextual Handwritten Recognition Systems based HMMs for Cursive Arabic and Latin Script

Arabic Hand Written Character Recognition Based on Contour Matching and Neural Network

Isolated Arabic Hand Written Letters Recognition Based on Contour Matching and Neural Network

Contact Info

Product

Resources

About