OCR Based Document Archiving and Indexing Using PyTesseract: A Record Management System for DSWD Caraga, Philippines

Small to large companies handle multiple forms of records every day. These organizations could use these records for historical, demographical, sociological, medical, or scientific research and serve as benchmarks to measure the organization's future activities and decisions. The Department of Social Worker and Development (DSWD) Caraga continuously generates records daily. Still, their records management system is conventional, giving them a hard time retrieving and keeping track of the record's whereabouts. With this, DSWD Caraga embarks into record's digitization for its management to ensure the preservation of permanent and valuable papers, secured and accessible for future reference as required by the organization's different offices based on existing rules and regulations in records management. This paper endeavors to automate records classification using the open-source Python-Tesseract (PyTesseract) library, the wrapper for Google's Tesseract-OCR Engine. The process starts by converting paper-based documents into digital format (scanning) and then recognize and extract the text using the PyTesseract library. By integrating this library to Django and MySQL, management of record's classification, indexing, and archiving becomes easy. With the help of this system, record's safekeeping and retrieval bring comfort for the records officer.