bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents
This addresses the problem of document digitization for Bengali speakers and researchers, though it is incremental as it builds on existing OCR components.
The authors tackled the lack of comprehensive open-source OCR systems for Bengali, a low-resource language, by introducing bbOCR, which reconstructs documents into a structured digitized format and outperforms current state-of-the-art Bengali OCR systems.
Despite the existence of numerous Optical Character Recognition (OCR) tools, the lack of comprehensive open-source systems hampers the progress of document digitization in various low-resource languages, including Bengali. Low-resource languages, especially those with an alphasyllabary writing system, suffer from the lack of large-scale datasets for various document OCR components such as word-level OCR, document layout extraction, and distortion correction; which are available as individual modules in high-resource languages. In this paper, we introduce Bengali$.$AI-BRACU-OCR (bbOCR): an open-source scalable document OCR system that can reconstruct Bengali documents into a structured searchable digitized format that leverages a novel Bengali text recognition model and two novel synthetic datasets. We present extensive component-level and system-level evaluation: both use a novel diversified evaluation dataset and comprehensive evaluation metrics. Our extensive evaluation suggests that our proposed solution is preferable over the current state-of-the-art Bengali OCR systems. The source codes and datasets are available here: https://bengaliai.github.io/bbocr.