This research addresses the crucial task of information retrieval from historical documents, specifically those from the 18th and 19th centuries. Optical Character Recognition (OCR) technology serves as a foundation for this process, enabling the conversion of scanned documents into machine-readable text format. A prominent OCR solution, Tesseract, was employed in this study due to its capability of recognizing a vast array of languages. This facilitated the extraction of valuable information and metadata from the digitized historical materials. Furthermore, standardized OCR-D processors were utilized to convert the raw data from its original PDF format into a structured TEI XML format. This transformation ensures the confidentiality and controlled access of the historical data for future research endeavors and analytical purposes. The implemented methodology offers a systematic approach to information gathering and retrieval from historical documents. This approach aligns with the broader efforts of digitalization and archival preservation, fostering continued exploration and understanding of historical records.

The contents of the files include the following,

1. All 24 document folders are uploaded here.
2. Each document folder has the processed pages after going through the processing steps by processors.
3. The final output folder has , combined hocr file , tei xml python code and tei xml output file.
4. python code for splitting tiff document into indiviual document and combining hocr code is also included in the main branch.
5. It also has our Report Document.