What question did this study set out to answer?

The main aim is to develop a deep learning-based application for recognizing pills from images with high accuracy.

January 25, 2026Open Access

MediScan AI: A Computer Vision and Deep Learning-Based Application

Key Points

The main aim is to develop a deep learning-based application for recognizing pills from images with high accuracy.
Developed a pill recognition system using Convolutional Neural Networks (CNNs)
Created a web application powered by Streamlit to facilitate user interaction
Tested the model with various images for accuracy measurement
Achieved over 90% accuracy in identifying pharmaceutical pills
Enabled real-time verification of pills through user-uploaded images
Supported use by pharmacists, patients, and supply chain professionals

Abstract

This project presents a deep learning-based pill recognition system that uses Convolutional Neural Networks (CNNs) to identify pharmaceutical pills from images with over 90% accuracy. A Streamlit-powered web application operationalizes this model, enabling users, including pharmacists, patients, and supply chain professionals to verify pills in real time using uploaded images.

AI से पूछें

Bookmark

View Full Paper