This project is an AI-based application that detects medication labels from camera input and provides the user with information and usage instructions about the identified medication. The project uses a machine learning model to recognize medication images and includes a text-to-speech feature that provides voice guidance for the detected medication.
- Camera-Based Medication Recognition: The application detects and identifies medications from the video feed.
- Medication Information and Usage Instructions: Information and usage instructions about the recognized medications are displayed on the screen and read aloud.
- Repeat Feature: The user can press a "Repeat" button to hear the information again.
- Responsive Design: The video and prediction overlay are responsive and adjust to different screen sizes.
- HTML5 and CSS3: For the structure and design of the application.
- JavaScript (with jQuery): For medication detection, model loading, and image processing functionality.
- Roboflow: Used for the medication detection model.
- Web Speech API: Utilized to read out the medication information and usage instructions.
To clone and run this project locally, follow these steps:
-
Clone the repository:
git clone /~https://github.com/your-username/medication-recognition-system.git
-
Obtain your API key from Roboflow and replace the
publishable_keyvariable in the JavaScript code:var publishable_key = "your_publishable_key";
-
Open the
index.htmlfile in your browser to start the application.
- When the application starts, your camera will be activated and the system will begin detecting medications.
- Information about the detected medications, including usage instructions, will be displayed on the screen and read out loud.
- Click the Repeat button to hear the information again.
Contributions are welcome! Please open an issue first to discuss what you would like to change, and then submit a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.