mlsanityData to 7 Oct 2026

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

arXiv 2402.10943 ↗First posted 8 Feb 2024cs.CL cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

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 pr'esente une 'etude d'exactitude du moteur ROC open source, Krakan, sur la revue acad'emique arabe de premier rang, al-Abhath. Contrairement `a d'autres moteurs ROC disponibles sur le march'e, Kraken se r'ev`ele etre capable de produire de la ROC extremement exacte de l''ecriture arabe. L''etude 'evalue aussi l'exactitude relative des mod`eles sp'ecifiquement configur'es `a des polices et celle des mod`eles g'en'eralis'es sur les donn'ees d'al-Abhath et fournit une microanalyse des "occurrences d'erreurs", ainsi qu'une microanalyse des 'el'ements contextuels qui pourraient avoir contribu'e `a la m'ereconnaissance ROC. S'appuyant sur cette analyse, cet article fait valoir que la ROC de l''ecriture arabe peut etre consid'erablement am'elior'ee grace `a (1) une approche plus syst'ematique d'entrainement de la production de donn'ees et (2) grace au d'eveloppement de composants technologiques fondamentaux, notammentl'am'elioration des mod`eles multilingues, de la segmentation de ligne et de l'analyse de la mise en page.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 3 of its 14 references that are in the map. First posted on arXiv 8 Feb 2024.

Builds on

3 of 14 references.

References · 3

  1. 2018Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latincited by 12
  2. 2019BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscriptscited by 12
  3. 2017Important New Developments in Arabographic Optical Character Recognition (OCR)cited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.