🧑‍⚕️ Acne Detection API using YOLOv8

This project provides an API for detecting acne in face images using YOLOv8. It highlights acne spots and generates a severity score based on the detected acne area.

---

🚀 Features

✅ Detects acne spots on facial images
✅ Generates severity score (Mild, Moderate, Severe)
✅ Returns a processed image with acne highlighted
✅ Built using FastAPI & YOLOv8
✅ Simple API to receive user data and image

---

🏗 Folder Structure

├── dataset/                  # Dataset directory
│   ├── train/
│   │   ├── images/
│   │   ├── labels/
│   ├── valid/
│   │   ├── images/
│   │   ├── labels/
│   ├── test/
│   │   ├── images/
│   │   ├── labels/
├── models/                   # Trained YOLOv8 model
├── results/                   # Processed images output
├── main.py                    # FastAPI backend
├── requirements.txt            # Dependencies
├── config.yaml                 # YOLOv8 dataset config
├── README.md                   # Project documentation

---

🔧 Installation

1️⃣ Clone the Repository

git clone https://github.com/yourusername/acne-detection-api.git
cd acne-detection-api

2️⃣ Create a Virtual Environment

python -m venv .venv
source .venv/bin/activate   # On Windows, use: .venv\Scripts\activate

3️⃣ Install Dependencies

pip install -r requirements.txt

---

🎯 Usage

1️⃣ Run the API Server

uvicorn app:app --host 0.0.0.0 --port 8000

2️⃣ Open API Documentation (Swagger UI)

Go to: http://127.0.0.1:8000/docs

You can test the API here by uploading an image and entering user details.

---

🔗 API Endpoints

🔹 POST /analyze_acne/

📌 Request: (multipart/form-data)

{
  "name": "John Doe",
  "age": 22,
  "file": "image.jpg"
}

📌 Response: (JSON)

{
  "name": "John Doe",
  "age": 22,
  "acne_spots": 10,
  "total_acne_area": 4500,
  "severity": "Moderate",
  "processed_image": "results/image.jpg"
}

---

🧪 Testing the API

1️⃣ Using Swagger UI

• Visit: http://127.0.0.1:8000/docs
• Click on POST /analyze_acne/
• Upload a face image and enter name & age
• Click Execute to get results

2️⃣ Using Postman

1. Open Postman
2. Create a POST request to http://127.0.0.1:8000/analyze_acne/
3. In Body (form-data):
   • name: Text (e.g., "John Doe")
   • age: Text (e.g., "22")
   • file: File (upload an image)
4. Click Send to receive results

3️⃣ Using cURL (Terminal)

curl -X 'POST' 'http://127.0.0.1:8000/analyze_acne/' \
  -F 'name=John Doe' \
  -F 'age=22' \
  -F 'file=@path/to/your/image.jpg'

---

📜 License

This project is open-source and available under the MIT License.

---

👨‍💻 Author

Developed by Seneth Mendis Kumarasignha
🔗 GitHub: github.com/senethmendis