MétaCan
Menu
Back to cohort
Record W4392200088 · doi:10.18280/isi.290102

An Arabic OCR Approach Using Levenshtein Distance and CNNs

2024· article· fr· W4392200088 on OpenAlexvenueno aff
Walid Fakhet, Salim El Khediri, Salah Zidi

Bibliographic record

VenueIngénierie des systèmes d information · 2024
Typearticle
Languagefr
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsnot available
Fundersnot available
KeywordsLevenshtein distanceArabicComputer scienceNatural language processingArtificial intelligenceEdit distancePattern recognition (psychology)Information retrievalLinguistics

Abstract

fetched live from OpenAlex

Recognition (AHCR) systems encounter various challenges arising from the unique characteristics of the Arabic language and the limited availability of public databases.Consequently, numerous research endeavors have aimed to enhance the recognition accuracy of AHCR.In this study, we propose a solution inspired by the intricate functions of the human visual cortex and hippocampus.Our proposed system employs a segmentation method to break down Arabic characters, and a Convolutional Neural Network (CNN) is then utilized for character recognition.To recognize entire words, we employ the Levenshtein distance with a personalized database containing an extensive collection of Arabic words.Experimental results demonstrate that our system yields a word error rate ranging from 1% to 25%, contingent upon the number of accurately recognized characters.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesScholarly communication
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.944
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0030.018
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.034
GPT teacher head0.271
Teacher spread0.237 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueIngénierie des systèmes d informationSame topicHandwritten Text Recognition TechniquesFrench-language works237,207