A Comparative Study of Optical Character Recognition in Health Information System

Abstract

Most Health Institutes are transitioning between documents in physical format and digital format. It is pertinent and important to develop applications that helps health professionals on this transition. An application that would aid the process of digitalization of documents was developed using a Python library. To help with the decision of which library to use, a study was made regarding the precision and speed of execution of PyOCR, PyTesseract and TesseOCR.