MEDetect Computer Vision Project
Updated 5 months ago
81
2
Metrics
Project by BS Computer Science Students from Polytechnic University of the Philippines
Addressing the global challenge of counterfeit over-the-counter medicines, particularly in the Philippines, the study introduces MEDetect—a system designed to recognize common over-the-counter acetaminophen tablets and blister packaging. Utilizing You Only Look Once version 8 (YOLOv8) with various data augmentation techniques, such as flip, rotation, blur, brightness, and crop, enhances the model's performance.
Ethical Considerations All medicines utilized in the research were obtained through legal and legitimate means. The researchers ensured compliance with all relevant laws, regulations, and ethical guidelines on acquiring medicinal products. In this regard, the researchers sought assistance from relevant authorities in the Philippines, including the Food and Drug Administration (FDA), and a pharmacist. The objective was to obtain sample photos of their collected counterfeit medications and data validation. Furthermore, the medicines gathered through primary sources were not intended for personal consumption or used as medication. Instead, they were specifically procured to build a comprehensive dataset to train, validate, and test the system.
It was crucial to emphasize that these medicines are never resold or distributed for any commercial purposes. Following the completion of the experimentation phase, all recognized fake or counterfeit drugs were transferred to the responsible authorities contributing to safeguarding public health and upholding ethical standards within the pharmaceutical industry, preventing these potentially harmful substances from re-entering circulation.
Moreover, it was important to note that the objective of the study was not to degrade, discredit, or discriminate against any specific brand or manufacturer. For that matter, the researchers masked the brand names of the medicines used in this study. The focus was solely on developing an accurate and effective system for recognizing authentic medicines. The researchers remained committed to the highest ethical standards and transparency throughout the research process. The researchers prioritized the well-being and safety of individuals and strive to conduct the work in a manner that upholds the principles of integrity, fairness, and respect for all stakeholders involved.
Use This Trained Model
Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
medetect-9kphx_dataset,
title = { MEDetect Dataset },
type = { Open Source Dataset },
author = { MEDetect },
howpublished = { \url{ https://universe.roboflow.com/medetect/medetect-9kphx } },
url = { https://universe.roboflow.com/medetect/medetect-9kphx },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { jun },
note = { visited on 2024-11-14 },
}