MétaCan
Menu
Back to cohort
Record W4200356778 · doi:10.16995/dscn.8094

Advances and Limitations in Open Source Arabic-Script OCR: A Case Study

2021· article· en· W4200356778 on OpenAlexvenueno aff
Benjamin Kiessling, Gennady Kurin, Matthew Thomas Miller, Kader Smail

Bibliographic record

VenueDigital Studies / Le champ numérique · 2021
Typearticle
Languageen
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsnot available
FundersNational Endowment for the Humanities
KeywordsTypefaceArabicOpen sourceHumanitiesNatural language processingArtificial intelligenceComputer scienceLinguisticsArtPhilosophyProgramming languageSoftware

Abstract

fetched live from OpenAlex

This work presents an accuracy study of the open source OCR engine, Kraken, on the leading Arabic scholarly journal, al-Abhath. In contrast with other commercially available OCR engines, Kraken is shown to be capable of producing highly accurate Arabic-script OCR. The study also assesses the relative accuracy of typeface-specific and generalized models on the al-Abhath data and provides a microanalysis of the “error instances” and the contextual features that may have contributed to OCR misrecognition. Building on this analysis, the paper argues that Arabic-script OCR can be significantly improved through (1) a more systematic approach to training data production, and (2) the development of key technological components, especially multi-language models and improved line segmentation and layout analysis./Cet article présente une étude d’exactitude du moteur ROC open source, Krakan, sur la revue académique arabe de premier rang, al-Abhath. Contrairement à d’autres moteurs ROC disponibles sur le marché, Kraken se révèle être capable de produire de la ROC extrêmement exacte de l’écriture arabe. L’étude évalue aussi l’exactitude relative des modèles spécifiquement configurés à des polices et celle des modèles généralisés sur les données d’al-Abhath et fournit une microanalyse des « occurrences d’erreurs », ainsi qu’une microanalyse des éléments contextuels qui pourraient avoir contribué à la méreconnaissance ROC. S’appuyant sur cette analyse, cet article fait valoir que la ROC de l’écriture arabe peut être considérablement améliorée grâce à (1) une approche plus systématique d’entraînement de la production de données et (2) grâce au développement de composants technologiques fondamentaux, notammentl’amélioration des modèles multilingues, de la segmentation de ligne et de l’analyse de la mise en page.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.024
metaresearch head score (Gemma)0.095
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.024
Threshold uncertainty score0.125

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0240.095
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.005
Science and technology studies0.0020.002
Scholarly communication0.0050.005
Open science0.0030.002
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0020.001

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 head0.070
GPT teacher head0.311
Teacher spread0.241 · 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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

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

Citations9
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueDigital Studies / Le champ numériqueSame topicHandwritten Text Recognition TechniquesFrench-language works237,207