Handwriting Recognition & Prescription Scanner

Abstract

Prescription errors due to illegible handwriting and misinterpretation pose a serious threat to patient safety, often leading to incorrect medication dispensation, adverse drug interactions, and treatment complications. This project introduces an innovative Prescription Scanner built using Python to streamline prescription interpretation and reduce human error. The system integrates Optical Character Recognition (OCR) and Natural Language Processing (NLP) to accurately digitize both handwritten and printed prescriptions. Tesseract OCR extracts text from printed prescriptions, while a deep learning-based handwriting recognition model enhances the accuracy of handwritten script interpretation. Once extracted, the text undergoes NLP processing to identify key prescription elements, such as drug names, dosages, and usage guidelines. Additionally, real-time integration with a pharmaceutical database enables automated validation, helping to detect potential medication errors, incorrect dosages, and dangerous drug interactions. Experimental evaluation on a diverse dataset demonstrated high accuracy, achieving over 85% for handwritten text and more than 95% for printed prescriptions. This system provides a reliable solution to enhance patient safety, reduce pharmacists' workload, and improve prescription documentation. Future developments could focus on expanding dataset diversity, refining recognition accuracy, and integrating with electronic health records for real-time use.