Abstract
Optical Character Recognition (OCR) is the electronic conversion of images of computer-written, typewritten, handwritten, or printed text into machine-encoded text from a scanned document and a photo of a document. In Ethiopia, documents such as historical, office, and official documents have been documented in handwritten and typewritten form, until recently. Thus, a large number of historical and essential documents are still in hard-copy form and at risk of disaster to be lost. Computer-written and handwritten OCR have been developed for different language characters including Ethiopian languages (Ethiopic characters), But not typewriter-written OCR for Ethiopic scripts. Like handwritten documents, large historical documents are typewritten documents in Ethiopia. Thus, the typewritten OCR is mandatory to preserve these documents. This study focuses on building an OCR model for typewritten documents that are written on Ethiopic characters. For the study, different Ethiopic characters have been collected from typewritten documents, and 290 distinct characters have been segmented to construct augmented data to form various character variations and simulate the complexities encountered in real-world typewritten Amharic texts and enhance the adaptability of the OCR model. This technique aims to approximate the diversity inherent in the data. The model training framework leverages the capabilities of Tesseract, an open-source OCR engine, in conjunction with the artificially generated training set. The Tesseract’s existing Amharic OCR model has been deployed as a base model, and the fine-tuning process has been adopted in a layered approach by employing 45,000 samples and spanning 4,800 iterations. The model has been evaluated using character error rate (CER). As per the evaluation, the model performed with 13% CER on the test set. For this study, the Tesseract model before fine-tuning and the Google Lense platform has been used as a baseline to evaluate the performance of the model. Accordingly, our model has outperformed both baselines by more than 10% margin.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gebremichael, H.T., Mengistu, T.M., Beyene, M.M., Mengistu, F.G.: OCR system for the recognition of ethiopic real-life documents. In: Berihun, M.L. (ed.) ICAST 2021. LNICST, vol. 411, pp. 559–574. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-93709-6_38
Teshome, A.: Recognition of Amharic Braille. Research gate (2009). https://doi.org/10.13140/RG.2.1.1306.3284, https://www.researchgate.net/publication/303773888_RECOGNITION_OF_AMHARIC_BRAILLE
Rahmati, M., et al.: Printed persian OCR system using deep learning. IET Image Process. 14(ch115), 3920–31 (2020). https://doi.org/10.1049/iet-ipr.2019.0728
Tesseract Documentation: Tesseract documentation | Tesseract OCR. https://tesseract-ocr.github.io/. Accessed 31 Oct 2023
i2OCR: i2OCR - Free Online OCR. https://www.i2ocr.com/. Accessed 31 Oct 2023
Vijayarani, S., Sakila, A.: Performance comparison of OCR tools. Int. J. UbiComp (IJU) 6(3), 19–30 (2015)
Shapovalov, Y.B., Zhanna, I.B., Artem, I.A., Viktor, B.S., Aleksandr, D.U.: The potential of using Google expeditions and google lens tools under STEM-education in Ukraine. arXiv preprint arXiv:1808.06465 (2018)
Abish, B., Chhetri, G.B., Bhattarai, K., Pandey, M.: Nepali OCR. (2023)
Easy OCR Converter: Free Online OCR in 100+ Languages. Free Convert Image to Text Online. https://www.easyocrconverter.com/. Accessed 31 Oct 2023
Cowell, J., Hussain, F.: Amharic character recognition using a fast signature based algorithm. In: Proceedings on Seventh International Conference on Information Visualization, 2003. IV 2003, pp. 384–389. IEEE (2003)
Assabie, Y., Bigun, J.: Lexicon-based offline recognition of amharic words in unconstrained handwritten text. In: 2008 19th International Conference on Pattern Recognition. IEEE (2008). https://doi.org/10.1109/ICPR.2008.4761145
Meshesha, M., Jawahar, C.V.: Optical character recognition of Amharic documents. Afr. J. Inf. Commun. Technol. 3(2) (2007)
Belay, B., Habtegebrial, T., Liwicki, M., Belay, G., Stricker, D.: Factored convolutional neural network for Amharic character image recognition. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 2906–2910. IEEE (2019)
Addis, D., Liu, C. M., Ta, V.D.: Printed ethiopic script recognition by using LSTM networks. In: 2018 International Conference on System Science and Engineering (ICSSE), pp. 1–6. IEEE (2018)
Samuel, M., Schmidt-Thieme, L., Sharma, D.P., Sinamo, A., Bruck, A.: Offline handwritten amharic character recognition using few-shot learning. In: Girma Debelee, T., Ibenthal, A., Schwenker, F. (eds.) Pan-African Conference on Artificial Intelligence. PanAfriCon AI 2022. Communications in Computer and Information Science, vol. 1800, pp. 233–244. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-31327-1_13
Abdurahman, F., Sisay, E., Fante, K.A.: AHWR-Net: offline handwritten amharic word recognition using convolutional recurrent neural network. SN Appl. Sci. 3, 1–11 (2021)
Gondere, M.S., Schmidt-Thieme, L., Sharma, D.P., Scholz, R.: Multi-script handwritten digit recognition using multi-task learning. J. Intell. Fuzzy Syst. 43(1), 355–364 (2022)
Malhotra, R., Addis, M.T.: End-to-end historical handwritten ethiopic text recognition using deep learning. IEEE Access 11, 99535–99545 (2023). https://doi.org/10.1109/ACCESS.2023.3314334
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Deneke, B.S. et al. (2024). Typewritten OCR Model for Ethiopic Characters. In: Debelee, T.G., Ibenthal, A., Schwenker, F., Megersa Ayano, Y. (eds) Pan-African Conference on Artificial Intelligence. PanAfriConAI 2023. Communications in Computer and Information Science, vol 2068. Springer, Cham. https://doi.org/10.1007/978-3-031-57624-9_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-57624-9_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-57623-2
Online ISBN: 978-3-031-57624-9
eBook Packages: Computer ScienceComputer Science (R0)