[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/langstream-2024-majeed-ancient-but-digitized-developing-handwritten/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Aramaic](https://md.mova.elamur.ai/free/en/docs/papers/arc/) / Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset # Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset **Authors:** Ameer Majeed; [Hossein Hassani](https://md.mova.elamur.ai/free/en/docs/papers/authors/hossein-hassani/) · **Year:** 2024 · **Venue:** arXiv:2408.13631 **Link:** [arxiv.org/abs/2408.13631](https://arxiv.org/abs/2408.13631) · library `langstream-2024-majeed-ancient-but-digitized-developing-handwritten` · **Licence:** [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) — summary only [**1** citations](https://openalex.org/works?filter=cites:W4402701547) openalex · 2026-10-18[**1** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/langstream-2024-majeed-ancient-but-digitized-developing-handwritten/) of the 140673 papers whose bibliographies we read[arXiv:2408.13631](https://openalex.org/S4306400194)[licence](http://creativecommons.org/licenses/by-nc-sa/4.0/) - [Publisher's page](https://arxiv.org/abs/2408.13631) - [PDF](https://arxiv.org/pdf/2408.13631) - [arXiv 2408.13631](https://arxiv.org/abs/2408.13631) - [OpenAlex](https://openalex.org/W4402701547) **Authors (2)** 1. [Ameer Majeed](https://openalex.org/A5111335206) h 1 · 1 citations · 1 works 2. [Hossein Hassani](https://openalex.org/A5002890988) [ORCID](https://orcid.org/0000-0002-8899-4016) · h 9 · 211 citations · 43 works Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart. ## What it is about The authors collect KHAMIS, 624 handwritten East Syriac sentences (line images with ground-truth text files), written by 31 students and one professor from a 20-verse poem. They fine-tune Tesseract's Syriac LSTM model on it with the tesstrain tool (learning rate 0.0001, 10,000 iterations) and compare three train/evaluation splits (90/10, 80/20, 70/30). The character error rate (CER) on the evaluation sets is about 9 to 10.5 per cent. On a separate test set of 13 samples written by people outside the group, with added noise, CER is 18.9 to 19.7 per cent and word error rate 62.8 to 65.4 per cent, which the authors report as about twice as good as the default Syriac model. Preprocessing is a mean blur and a global threshold. The authors argue that CER should be the main metric, because WER marks a whole word wrong for one bad character. ## Ideas - I1. Make a fixed, held-out line-image set with ground truth for `tools/ocrfix`, scored by CER first and WER second, with the split reported as well. Use it before and after each correction step, so that the gain is measured and not assumed. - I2. Add the paper's preprocessing as the first stage of `tools/ocrfix` for scanned Hebrew and Aramaic editions: grayscale, mean blur, global threshold. Measure CER on the same pages with and without it. - I3. A robustness test built the paper's way: text written by people outside the training group, with one word swapped for a name and random characters replaced. The same noise recipe applied to Hebrew lines shows how much the correction step can recover. ## For Mova I1, I2 and I3 go into `tools/ocrfix`. The letter-form variants that the paper describes (final forms, the kaf and nun shapes) are a check for [1. Script and pointing](https://md.mova.elamur.ai/free/en/docs/languages/hbo/01-script/). The dataset itself is NC and is not used; only the protocol is taken. ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [arXiv 2408.13631](https://arxiv.org/abs/2408.13631) ``` @misc{majeed2024ancient, title = {{Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset}}, author = {Majeed, Ameer and Hassani, Hossein}, year = {2024}, eprint = {2408.13631}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.13631} } ``` - [← previous BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2022-chen-btpk-based-interpretable-method-ner/) - [next → NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-nazari-nolor-asr-based-framework-expedited/) - [↑ back to Aramaic](https://md.mova.elamur.ai/free/en/docs/papers/arc/) ## References 21 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Ackroyd, P.R., Evans, C.F. (eds.): The Cambridge History of the Bible: Volume 1, From the Beginning to Jerome. Cambridge University Press, Cambridge, England (1970) [find](https://scholar.google.com/scholar?q=Ackroyd%2C+P%2ER%2E%2C+Evans%2C+C%2EF%2E+%28eds%2E%29%3A+The+Cambridge+History+of+the+Bible%3A+Volume+1%2C+From+the+Beginning+to+Jerome%2E+Cambridge+University+Press%2C+Cambridge%2C+England+%281970%29) 2. Alvermann, D.: Word Error Rate & Character Error Rate – How to evaluate a model (2019). [https://shorturl.at/88GVf](https://shorturl.at/88GVf) [↗](https://shorturl.at/88GVf) 3. Amrouch, M., Rabi, M., Es-Saady, Y.: Convolutional feature learning and cnn based hmm for arabic handwriting recognition. In: Mansouri, A., El Moataz, A., Nouboud, F., Mammass, D. (eds.) Image and Signal Processing, pp. 265–274. Springer, Cham (2018) [find](https://scholar.google.com/scholar?q=Amrouch%2C+M%2E%2C+Rabi%2C+M%2E%2C+Es%2DSaady%2C+Y%2E%3A+Convolutional+feature+learning+and+cnn+based+hmm+for+arabic+handwriting+recognition%2E+In%3A+Mansouri%2C+A%2E%2C+El+Moataz%2C+A%2E%2C+Nouboud%2C+F%2E%2C+Mammass%2C+D%2E+%28eds%2E%29+Image+and+Sig) 4. Bilane, P., Bres, S., Emptoz, H.: Local orientation extraction for wordspotting in syriac manuscripts. In: Elmoataz, A., Lezoray, O., Nouboud, F., Mammass, D. (eds.) Image and Signal Processing, pp. 481–489. Springer, Berlin, Heidelberg (2008) [find](https://scholar.google.com/scholar?q=Bilane%2C+P%2E%2C+Bres%2C+S%2E%2C+Emptoz%2C+H%2E%3A+Local+orientation+extraction+for+wordspotting+in+syriac+manuscripts%2E+In%3A+Elmoataz%2C+A%2E%2C+Lezoray%2C+O%2E%2C+Nouboud%2C+F%2E%2C+Mammass%2C+D%2E+%28eds%2E%29+Image+and+Signal+Processing%2C+pp%2E+4) 5. Butts, A.M.: Syriac Syriac-Language Language Clocksin, W.F., Fernando, P.J.: Towards Automatic Transciption of Syriac Handwriting. In: 12th International Conference on Image Analysis and Processing. IEEE, Mantova, Italy (2003) [find](https://scholar.google.com/scholar?q=Butts%2C+A%2EM%2E%3A+Syriac+Syriac%2DLanguage+Language+Clocksin%2C+W%2EF%2E%2C+Fernando%2C+P%2EJ%2E%3A+Towards+Automatic+Transciption+of+Syriac+Handwriting%2E+In%3A+12th+International+Conference+on+Image+Analysis+and+Processing%2E+I) 6. Chesley, E., Marcantonio, J., Pearson, A.: Towards syriac digital corpora: Evaluation of tesseract 4.0 for syriac ocr. Hugoye: Journal of Syriac Studies (2019) [find](https://scholar.google.com/scholar?q=Chesley%2C+E%2E%2C+Marcantonio%2C+J%2E%2C+Pearson%2C+A%2E%3A+Towards+syriac+digital+corpora%3A+Evaluation+of+tesseract+4%2E0+for+syriac+ocr%2E+Hugoye%3A+Journal+of+Syriac+Studies+%282019%29) 7. Dehghan, M., Faez, K., Ahmadi, M., Shridhar, M.: Handwritten farsi (arabic) word recognition: a holistic approach using discrete hmm. Pattern Recognition 34(5), 1057–1065 (2001) [find](https://scholar.google.com/scholar?q=Dehghan%2C+M%2E%2C+Faez%2C+K%2E%2C+Ahmadi%2C+M%2E%2C+Shridhar%2C+M%2E%3A+Handwritten+farsi+%28arabic%29+word+recognition%3A+a+holistic+approach+using+discrete+hmm%2E+Pattern+Recognition+34%285%29%2C+1057%E2%80%931065+%282001%29) 8. Davis, R.H., Lyall, J.: Recognition of handwritten characters - a review. Image and Vision Computing (1986) [find](https://scholar.google.com/scholar?q=Davis%2C+R%2EH%2E%2C+Lyall%2C+J%2E%3A+Recognition+of+handwritten+characters+%2D+a+review%2E+Image+and+Vision+Computing+%281986%29) 9. Fermanian, R., Yaacoub, C., Bilane, P.: Deep recognition-based character segmentation in handwritten syriac manuscripts. In: 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA) (2020) [find](https://scholar.google.com/scholar?q=Fermanian%2C+R%2E%2C+Yaacoub%2C+C%2E%2C+Bilane%2C+P%2E%3A+Deep+recognition%2Dbased+character+segmentation+in+handwritten+syriac+manuscripts%2E+In%3A+2020+Tenth+International+Conference+on+Image+Processing+Theory%2C+Tools+and+A) 10. Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Pearson, N/A (2018) [find](https://scholar.google.com/scholar?q=Gonzalez%2C+R%2EC%2E%2C+Woods%2C+R%2EE%2E%3A+Digital+Image+Processing%2E+Pearson%2C+N%2FA+%282018%29) 11. Hamid, A., Haraty, R.: A neuro-heuristic approach for segmenting handwritten arabic text. In: Proceedings ACS/IEEE International Conference on Computer Systems and Applications (2001) [find](https://scholar.google.com/scholar?q=Hamid%2C+A%2E%2C+Haraty%2C+R%2E%3A+A+neuro%2Dheuristic+approach+for+segmenting+handwritten+arabic+text%2E+In%3A+Proceedings+ACS%2FIEEE+International+Conference+on+Computer+Systems+and+Applications+%282001%29) 12. Khorsheed, M.S.: Recognising handwritten arabic manuscripts using a single hidden markov model. Pattern Recognition Letters 24(14), 2235–2242 (2003) [find](https://scholar.google.com/scholar?q=Khorsheed%2C+M%2ES%2E%3A+Recognising+handwritten+arabic+manuscripts+using+a+single+hidden+markov+model%2E+Pattern+Recognition+Letters+24%2814%29%2C+2235%E2%80%932242+%282003%29) 13. Lorigo, L., Govindaraju, V.: Segmentation and pre-recognition of arabic handwriting. In: Eighth International Conference on Document Analysis and Recognition (ICDAR’05). IEEE, Seoul, Korea (South) (2005) [find](https://scholar.google.com/scholar?q=Lorigo%2C+L%2E%2C+Govindaraju%2C+V%2E%3A+Segmentation+and+pre%2Drecognition+of+arabic+handwriting%2E+In%3A+Eighth+International+Conference+on+Document+Analysis+and+Recognition+%28ICDAR%E2%80%9905%29%2E+IEEE%2C+Seoul%2C+Korea+%28South%29+%2820) 14. Mengozzi, A.: Khamis bar Qardahe (2011). [https://gedsh.bethmardutho.org/Khamis-bar-Qardahe](https://gedsh.bethmardutho.org/Khamis-bar-Qardahe) [↗](https://gedsh.bethmardutho.org/Khamis-bar-Qardahe) 15. Maalej, R., Kherallah, M.: Convolutional neural network and blstm for offline arabic handwriting recognition. In: 2018 International Arab Conference on Information Technology (ACIT), pp. 1–6 (2018) [find](https://scholar.google.com/scholar?q=Maalej%2C+R%2E%2C+Kherallah%2C+M%2E%3A+Convolutional+neural+network+and+blstm+for+offline+arabic+handwriting+recognition%2E+In%3A+2018+International+Arab+Conference+on+Information+Technology+%28ACIT%29%2C+pp%2E+1%E2%80%936+%282018%29) 16. Maalej, R., Tagougui, N., Kherallah, M.: Recognition of handwritten arabic words with dropout applied in mdlstm. In: Image Analysis and Recognition, pp. 746–752. Springer, Cham (2016) [find](https://scholar.google.com/scholar?q=Maalej%2C+R%2E%2C+Tagougui%2C+N%2E%2C+Kherallah%2C+M%2E%3A+Recognition+of+handwritten+arabic+words+with+dropout+applied+in+mdlstm%2E+In%3A+Image+Analysis+and+Recognition%2C+pp%2E+746%E2%80%93752%2E+Springer%2C+Cham+%282016%29) 17. Omniglot: Syriac Alphabet (2023). [https://www.omniglot.com/writing/syriac.htm](https://www.omniglot.com/writing/syriac.htm) [↗](https://www.omniglot.com/writing/syriac.htm) 18. OpenCV: OpenCV: Smoothing Images (2024). [https://docs.opencv.org/4.x/d4/d13/](https://docs.opencv.org/4.x/d4/d13/) [↗](https://docs.opencv.org/4.x/d4/d13/) 19. (2011). [https://gedsh.bethmardutho.org/tutorial](https://gedsh.bethmardutho.org/tutorial) py filtering.html Sayre, K.M.: Machine recognition of handwritten words: A project report. In: Pattern Recognition, vol. 5, pp. 213–228 (1973). Pergamon Press The Republic of Iraq: Constitution Project (2005). https://www.constituteproject. org/constitution/Iraq 2005 [↗](https://gedsh.bethmardutho.org/tutorial) 20. Tesseract-OCR: Tesseract-OCR (2024). [https://github.com/tesseract-ocr/tesseract](https://github.com/tesseract-ocr/tesseract) [↗](https://github.com/tesseract-ocr/tesseract) 21. UNESCO: World Atlas of Languages (2010). [https://en.wal.unesco.org/discover/languages?text=aramaic](https://en.wal.unesco.org/discover/languages?text=aramaic) [↗](https://en.wal.unesco.org/discover/languages?text=aramaic)