Manual food tracking is often inaccurate, time-consuming, and inconvenient. Existing methods rely on barcode scanning or manual input, which may not always be available or practical. To address this, an automated food recognition system using AI is needed to accurately identify food items, brands, and nutritional information in real-time.

• AI Model & Object Detection: We utilize YOLO (You Only Look Once), a real-time object detection algorithm, to train a model on a food dataset.
• Hardware Setup: The trained YOLO model is deployed on a Raspberry Pi with a camera module for real-time image processing.
• Processing Pipeline:
  1. The camera captures images of food items.
  2. YOLO detects and classifies the food items and brands.
  3. The system retrieves calorie and nutrition data from a pre-built database.
  4. The results are displayed for the user.

• The system’s accuracy is tested using benchmark food datasets.
• Performance metrics such as precision, recall, and F1-score are used to evaluate the model’s effectiveness.
• Real-world testing identifies various food items and compares the AI’s predictions with actual nutritional values.

The YOLO-based food recognition system demonstrates high accuracy in real-time identification of food items, brands, and nutrition data. This solution offers potential applications in diet tracking, health monitoring, and automated nutrition analysis, making food logging easier and more efficient.

www.github.com

https://docs.ultralytics.com/

https://colab.research.google.com/

https://labelstud.io/

would like to thank my teacher, mr maruyama , for their help and support during this project. Their guidance was very important to me. I also want to thank my family and friends for their encouragement and patience. Their support made this project possible.