Semi-automatic document processing and text-recognition for digital transformation of low-resources organizations

Abstract

The digital transformation of organizations has become critical for their survival. Smaller organizations, and especially those in developing countries, are facing bigger challenges in this process due to limited resources and lack of digital skills. One of the keys of this transformation is the digitalization of information, where optical character recognition (OCR) plays an essential role. This research analyzes current OCR tools and systems for document digitalization in low-resources organizations and presents a semi-automatic document processing and text-recognition solution that addresses their needs. The study then presents an experimental design to assess the efficiency of the tool. The results support the adequacy of using these tools, compared to current manual digitalization processes.