A Comparative Analysis of the Accuracy and Efficiency of OCR Tools in Digital Archiving at Government Agencies in Malang City
DOI:
https://doi.org/10.62951/ijbmir.v3i3.221Keywords:
Comparative Performance Evaluation, Digital Archives, Document Digitization, Government Administration, Optical Character Recognition (OCR)Abstract
The digitization of government archives frequently yields non-machine-readable image files, limiting searchability and administrative utility. This study comparatively evaluates the accuracy and efficiency of four Optical Character Recognition (OCR) tools (Tesseract, Google Vision, ABBYY FineReader, and Microsoft OCR) applied to administrative archives from government agencies in Malang City. Employing a comparative quantitative evaluative design, the research measures performance using Character Error Rate (CER), Word Error Rate (WER), and document processing time across purposively sampled documents. Data were analyzed via descriptive statistics and One-Way ANOVA. Results indicate that ABBYY FineReader achieves the highest accuracy (mean CER: 0.041; WER: 0.078), whereas Google Vision OCR demonstrates optimal processing efficiency (mean: 3.44 s). ANOVA confirms statistically significant performance differences across all metrics (p < 0.05), revealing a clear accuracy–efficiency trade-off. These findings demonstrate that no single tool universally dominates; rather, OCR selection must align with document criticality and institutional workflow demands. Consequently, high-precision archives benefit from accuracy-optimized systems, while high-volume digitization prioritizes computational speed. This research provides empirical evidence for context-driven OCR implementation, offering public institutions a structured decision framework to enhance digital archive accessibility, administrative efficiency, and long-term information management sustainability.
References
Abdallah, A., Eberharter, D., Pfister, Z., & Jatowt, A. (2024). A survey of recent approaches to form understanding in scanned documents. Artificial Intelligence Review, 57(342), 1–38. https://doi.org/10.1007/s10462-024-11000-0
Breuel, T. M. (2008). The OCRopus open source OCR system. Proceedings of SPIE, Document Recognition and Retrieval XV, 6815, Article 68150F. https://doi.org/10.1117/12.783598
Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., & Ha, D. (2018). Deep learning for classical Japanese literature. Journal of Imaging, 4(5), Article 65. https://doi.org/10.3390/jimaging4050065
Correia, S., & Luck, S. (2023). Digitizing historical balance sheet data: A practitioner’s guide. Explorations in Economic History, 87, Article 101475. https://doi.org/10.1016/j.eeh.2022.101475
de Oliveira, L. L., Vargas, D. S., Alexandre, A. M., Cordeiro, F. C., Gomes, D. D., Rodrigues, M. D., et al. (2023). Evaluating and mitigating the impact of OCR errors on information retrieval. International Journal on Digital Libraries, 24(1), 45–62. https://doi.org/10.1007/s00799-023-00345-6
Drobac, S., & Lindén, K. (2020). Optical character recognition with neural networks and post-correction with finite state methods. International Journal on Document Analysis and Recognition (IJDAR), 23(4), 279–295. https://doi.org/10.1007/s10032-020-00359-9
Fleischhacker, D., Kern, R., & Göderle, W. (2025). Enhancing OCR in historical documents with complex layouts through machine learning. International Journal on Digital Libraries, 26(1). https://doi.org/10.1007/s00799-025-00413-z
Google Cloud. (2024). Cloud Vision API documentation. https://cloud.google.com/vision/docs/ocr
Gupta, M. R., Jacobson, N. P., & Garcia, E. K. (2007). OCR binarization and image pre-processing for searching historical documents. Pattern Recognition, 40(2), 389–397. https://doi.org/10.1016/j.patcog.2006.04.043
Martínek, J., Lenc, L., & Král, P. (2020). Building an efficient OCR system for historical documents with little training data. Neural Computing and Applications, 32(3), 17209–17227. https://doi.org/10.1007/s00521-020-04910-x
Nagy, G. (2016). Disruptive developments in document recognition. Pattern Recognition Letters, 79, 106–112. https://doi.org/10.1016/j.patrec.2015.11.024
Sangiacomo, A., Hogenbirk, H. D., Tanasescu, R., Karaisl, A., & White, N. (2022). Reading in the mist: High-quality optical character recognition based on freely available early modern digitized books. Digital Scholarship in the Humanities, 37(4), 1197–1209. https://doi.org/10.1093/llc/fqab106
Singh, L. G., & Middleton, S. E. (2025). Tabular context-aware optical character recognition and tabular data reconstruction for historical records. International Journal on Document Analysis and Recognition (IJDAR), 28(3), 357–376. https://doi.org/10.1007/s10032-025-00543-9
Sivankalai, S., & Balachandran, S. (2025). Transforming physical archives into searchable digital libraries with optical character recognition. Preservation, Digital Technology & Culture, 54(4), 263–284. https://doi.org/10.1515/pdtc-2025-0025
Smith, R. (2007). An overview of the Tesseract OCR engine. Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), 629–633. https://doi.org/10.1109/ICDAR.2007.4376991
Smith, R. (2009). Hybrid page layout analysis via tab-stop detection. Proceedings of the 10th International Conference on Document Analysis and Recognition (ICDAR 2009), 241–245. https://doi.org/10.1109/ICDAR.2009.64
Vercruysse, B., Birkholz, J. M., Chandrasekar, K. K., Muheki, D., Thiery, W., Verbeeck, H., et al. (2025). Human-in-the-loop tabular data extraction methods for historical climate data rescue. International Journal on Document Analysis and Recognition (IJDAR), 29(1), 1–15. https://doi.org/10.1007/s10032-025-00524-y
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal Business, Management and Innovation Review

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.






