A novel approach for the recognition of a wide Arabic handwritten word lexicon

Cheikh, Imen Ben; Belaïd, Abdel; Kacem, Afef

doi:10.1109/icpr.2008.4761148

Cited by 9 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This work shows that giving slightly higher weight to linguistic information offers not only better results, but also solutions to handle wider vocabulary. In comparison with our previous work [2], the taking into account of the above improvements (letters order, "sister letters", neurons splitting up, networks supervising and ambiguity solving) has proven to significantly help the model reach its classification goal. Results are provided and show that, even without considering yet the suggested improvement proper to the recognition stage (perceptive cycles and linguistic constraints), our approach always produces higher success rates than the current approaches with regard to the vocabulary size as illustrated in table 1.…”

Section: Discussionmentioning

confidence: 89%

“…In [2], we proposed an approach for the recognition of a wide Arabic canonical vocabulary. The idea is to integrate linguistic knowledge to a perceptive model by the use of transparent neural networks (TNN), having as input global primitives of words.…”

Section: Neural-linguistic Approachmentioning

confidence: 99%

“…Current trends are for incorporating linguistic knowledge, at various levels (lexical, syntactic and semantic), either keeping them as an independent stage, or integrating them partly or totally in the recognition chain [1]. In this context, we proposed, in a previous work [2], a neural-linguistic approach based on two neural networks: TNN_R and TNN_S to respectively recognize the root, from which the word derives, and the scheme, the word follows, by the use of linguistic knowledge. Carried experiments demonstrated that results are promising.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A neural-linguistic approach for the recognition of a wide Arabic word lexicon

Cheikh¹,

Kacem²,

Belaïd

2010

Document Recognition and Retrieval XVII

Self Cite

View full text Add to dashboard Cite

Recently, we have investigated the use of Arabic linguistic knowledge to improve the recognition of wide Arabic word lexicon. A neural-linguistic approach was proposed to mainly deal with canonical vocabulary of decomposable words derived from tri-consonant healthy roots. The basic idea is to factorize words by their roots and schemes. In this direction, we conceived two neural networks TNN_R and TNN_S to respectively recognize roots and schemes from structural primitives of words. The proposal approach achieved promising results. In this paper, we will focus on how to reach better results in terms of accuracy and recognition rate. Current improvements concern especially the training stage. It is about 1) to benefit from word letters order 2) to consider "sisters letters" (having same features), 3) to supervise networks behaviours, 4) to split up neurons to save letter occurrences and 5) to solve observed ambiguities. Considering theses improvements, experiments carried on 1500 sized vocabulary show a significant enhancement: TNN_R (resp. TNN_S) top4 has gone up from 77% to 85.8% (resp. from 65% to 97.9%). Enlarging the vocabulary from 1000 to 1700 by 100 words, again confirmed the results without altering the networks stability.

show abstract

Section: Discussionmentioning

confidence: 89%

Section: Neural-linguistic Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A neural-linguistic approach for the recognition of a wide Arabic word lexicon

Cheikh¹,

Kacem²,

Belaïd

2010

Document Recognition and Retrieval XVII

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, from the root K -T -B ( ), lemmas are formed using Arabic schemes, e.g., (" ", "a library"), and by adding the prefix " " and the suffix " " to the lemma, we obtain the word (" ", "and in their library") [8][9][10]. In our study of Arabic user attitudes toward search engines [11], we found that query paraphrasing is a common search strategy.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Arabic Document Retrieval Using Optimized Query Paraphrasing

Aldayel

Ykhlef

2015

Arab J Sci Eng

View full text Add to dashboard Cite

Query paraphrasing aims to construct a better formulation of user queries in order to enhance retrieval. Formulating search queries remains complicated for a subset of Web users. In a typical situation, a user will not receive satisfactory results from the submitted search query and will subsequently attempt different query paraphrases. The Arabic vocabulary is rich in synonyms and hyponyms. Such richness of synonyms makes automation of the paraphrasing technique crucial for Arabic information retrieval systems in order to facilitate the process of paraphrasing synonyms. In this article, we propose an enhancement for Arabic information retrieval using a query paraphrasing technique. Furthermore, two query paraphrasing optimization techniques are proposed to overcome the time complexity and exhaustive calculation of existing query paraphrasing techniques. One of these techniques uses a genetic algorithm (GA-QP), and the other employs the artificial bee colony algorithm (ABC-QP). The performance of these two algorithms is compared. ABC-QP shows an improvement in Arabic information retrieval performance compared with the genetic algorithm query paraphrasing system. B Abeer Al-Dayel

show abstract

“…To this end, word morphological analysis and factorization seem to be one solution. Actually, in this context, we have already proposed, in a previous work (Ben et al, 2008); (Ben et al, 2010), a classifiers combination based approach that uses linguistic knowledge to simplify the enormous number of Arabic words. The simplification was based on word factorization in morphological entities (root, schemes and conjugation) since we deal with decomposable words.…”

Section: Introductionmentioning

confidence: 99%

HMM based Classifier for the Recognition of Roots of a Large Canonical Arabic Vocabulary

Cheikh

Zouaoui

2013

Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

The complexity of the recognition process is strongly related to language, the type of writing and the vocabulary size. Our work represents a contribution to a system of recognition of large canonical Arabic vocabulary of decomposable words derived from tri-consonantal roots. This system is based on a collaboration of three morphological classifiers specialized in the recognition of roots, schemes and conjugations. Our work deals with the first classifier. It is about proposing a root classifier based on 101 Hidden Markov Models, used to classify 101 tri-consonantal roots. The models have the same architecture endowed with Arabic linguistic knowledge. The proposed system deals, up to now, with a vocabulary of 5757 words. It has been learned then tested using a total of more than 17000 samples of printed words. Obtained results are satisfying and the top2 recognition rate reached 96%.

show abstract

A novel approach for the recognition of a wide Arabic handwritten word lexicon

Cited by 9 publications

References 3 publications

A neural-linguistic approach for the recognition of a wide Arabic word lexicon

A neural-linguistic approach for the recognition of a wide Arabic word lexicon

Enhanced Arabic Document Retrieval Using Optimized Query Paraphrasing

HMM based Classifier for the Recognition of Roots of a Large Canonical Arabic Vocabulary

Contact Info

Product

Resources

About