Installation Instructions

Setup

1. Install the latest version of python
2. Install the Pycharm Community Edition IDE
3. Create a new (empty) Pycharm project in a folder called "TrashVision"
4. Download the TrashVision.zip file, and extract all contents into the TrashVision folder
5. Install the required Python packages using the following commands:
   • pip install flask
     • pip install flask_cors
     • pip install roboflow
6. Ensure that the user_uploads directory exists in the project directory.

Usage

1. Run the main.py file by opening it in Pycharm and pressing Alt+Shift+10 or clicking the icon in the top rigt corner.
2. Open interface.html in your preferred web browser.
3. Place the image you want to analye in any directory other than the user_uploads folder (Desktop or Downloads is a good option).

   > Make sure there is no prediction.jpg file present before doing the image analysis. If there is, please remove it, since the program may behave unexpectedly.

         > Recommended Resolution: 1280x720

1. Click the "Choose File" button and select the image inside the user_uploads folder.
2. Click the "Upload Image" button to submit the image for analysis.

   > Make sure that the image you want analyzed is not inside the user_uploads directory. <-IMPORTANT

3. The application will display the analyzed image below the upload field shortly after.

Important Notes

• Ensure that the user_uploads folder exists and is accessible to the application.
• Images should be well-lit and clearly show the trash item for accurate recognition.
• If there is an existing prediction.jpg file in the user_uploads directory, remove it before doing the image analysis.

Disclaimer

• This project is developed as a proof of concept and may require further refinement for production use.
• The accuracy of trash recognition may vary alot based on the quality of the input image and the model's training data.
• The Report a Bug button does not work as expected at the moment.