Prescription-to-Text Conversion Using Ensemble Faster R-CNN with Optical Character Recognition

Automated extraction of textual information from medical prescriptions is a critical task in healthcare, enabling efficient digitization and reducing manual errors. This paper presents a novel approach that leverages Faster R-CNN for prescription localization and Optical Character Recognition (OCR) for text extraction. The Faster R-CNN model is trained to detect and segment regions of interest within handwritten and printed prescriptions, ensuring accurate localization of textual components such as drug names, dosages, and patient details. The extracted regions are then processed using OCR techniques to convert the detected text into a structured digital format. The proposed method is evaluated on a dataset of medical prescriptions, demonstrating high accuracy in both detection and recognition tasks. This system can be integrated into healthcare applications for automated prescription processing, improving efficiency in medical record management and patient care.