Medicine Drug Name Detection Object Recognition using Deep Learning based OCR System

In a digital picture, such as a photo, document, or any other image with tags or steps, OCR is a system that can identify characters like letters, numbers, and symbols. Pre- processing is the initial stage in which the EAST pre-processes images to improve the chances of successful detection. The EAST (Efficient and Accurate Scene Text) algorithm is a deep learning-based method for detecting and recognizing text in images. EAST is known for its speed and accuracy in handling text detection tasks in various applications, such as OCR (Optical Character Recognition). The Tesseract model is an optical character recognition engine which finds pixels, letters, words and sentences. OCR can be employed to extract text from images of medicine labels. The name of the drug is extracted from the label using the EAST and Tesseract models, which help low-vision individuals read the medication name.