Detecting and Extracting Information of Medicines from a Medical Prescription Using Deep Learning and Computer Vision

Usually, reading any person's handwriting becomes slightly a challenging task for one. Similarly, when it comes to a doctor's handwriting in their medical prescription it becomes the most challenging task to the patients, general people and few medical related workers encountering this as an issue, in certain cases, it heads towards wrong concerns or results due to incorrect decoding of any medical prescription written by a doctor. Out of all things the main reason one cannot interpret a doctor's handwriting in their medical prescription isthat doctors use the Greek and other foreign medical terms andabbreviations that any person won't recognize or understand. This paper establishes how Long Short-Term Memory (LSTM) based Convolutional Neural Network (CNN) is used to develop a model that can distinguish doctor's handwriting in their medical prescriptions. Utilizing the Deep Convolution Recurrent Neural Network (RNN) to train this supervising model, input pictures are segmented using Otsu segmentation and handled to identify the letters and words and categorize them into the 56 various defined characters