The motivation for this project is to help people get better understanding about the medicine they are using and help them provide them all information on their finger tip.
The process will start with drug image as input and it will straight away be fed to the Tesseract OCR model, Tesseract OCR consists of trained language models (>192), different kinds of recognition (image as word, text block, vertical text). To extract all the text in the provided image and present it in a digitally accepted text format.
To get started, clone the repository to your local machine: