Object Detection In Images

A powerful object detection application capable of identifying objects in uploaded images using the YOLOv8 model. This project features a Flask backend and a user-friendly frontend interface.

---

🚀 Technologies Used

---

📂 Project Structure

Object Detection In Images/
├── static/
│   ├── index.html      # Frontend interface
│   ├── script.js       # Frontend logic
│   └── style.css       # Styling
├── templates/          # Flask templates
├── uploads/            # Directory for uploaded images
├── app.py              # Flask application entry point
├── detector.py         # Object detection logic using YOLO
├── requirements.txt    # Project dependencies
├── yolov8n.pt          # YOLOv8 nano model weights
├── yolov8m.pt          # YOLOv8 medium model weights
├── .gitignore
└── README.md

---

🛠️ Installation & Setup

Prerequisites

• Python - for compiling the code
• Git - for downloading this project
• Git LFS - Enable Git LFS for downloading YOLOv8 models

Steps

1. Clone the repository:

   git clone https://github.com/Maheswara660/Object-Detection-In-Images.git
   cd Object-Detection-In-Images
   git lfs install
   git lfs pull

2. Set up the Virtual Environment:

   Navigate to the project root and create a virtual environment.

   • macOS/Linux:

     python3 -m venv venv
     source venv/bin/activate

   • Windows (Command Prompt):

     python -m venv venv
     venv\Scripts\activate.bat

   • Windows (PowerShell):

     python -m venv venv
     venv\Scripts\Activate.ps1

3. Install Dependencies: Install the required packages from requirements.txt.

   pip install -r requirements.txt

---

▶️ Usage & Execution

Running the Application

Ensure your virtual environment is activated and you are in the project root directory.

# Set Flask app environment variable (optional but recommended)
export FLASK_APP=app.py
export FLASK_ENV=development

# Run the application
flask run

Or simply run:

python app.py

The application will start at http://127.0.0.1:5000/.

Using the Interface

1. Open your web browser and navigate to http://localhost:5000.
2. Upload an image using the upload button.
3. Adjust the confidence threshold if needed.
4. View the detected objects and their bounding boxes on the processed image.

---

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.