{"id":26689608,"url":"https://github.com/nvhnam/fooddetector","last_synced_at":"2026-05-01T15:40:02.893Z","repository":{"id":287730791,"uuid":"840332418","full_name":"nvhnam/FoodDetector","owner":"nvhnam","description":"A web application that use a YOLOv10b model, got mAP50 of 0.92, trained on the VietFood67 dataset to perform real-time Vietnamese food recognizing.","archived":false,"fork":false,"pushed_at":"2025-05-14T12:38:41.000Z","size":467605,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"v2","last_synced_at":"2025-05-14T13:54:01.066Z","etag":null,"topics":["food-detection","object-detection","opencv","python","real-time","roboflow","rtsp-stream","streamlit","vietfood67","yolov10"],"latest_commit_sha":null,"homepage":"https://fooddetectorv2.streamlit.app/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nvhnam.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-08-09T13:19:15.000Z","updated_at":"2025-05-14T12:38:44.000Z","dependencies_parsed_at":"2025-05-14T13:39:14.757Z","dependency_job_id":"a45e96ff-77b5-4a5d-8ef5-3ea173bd77df","html_url":"https://github.com/nvhnam/FoodDetector","commit_stats":null,"previous_names":["nvhnam/fooddetector"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nvhnam/FoodDetector","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nvhnam%2FFoodDetector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nvhnam%2FFoodDetector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nvhnam%2FFoodDetector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nvhnam%2FFoodDetector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nvhnam","download_url":"https://codeload.github.com/nvhnam/FoodDetector/tar.gz/refs/heads/v2","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nvhnam%2FFoodDetector/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32503203,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["food-detection","object-detection","opencv","python","real-time","roboflow","rtsp-stream","streamlit","vietfood67","yolov10"],"created_at":"2025-03-26T14:38:57.690Z","updated_at":"2026-05-01T15:40:02.869Z","avatar_url":"https://github.com/nvhnam.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🕵️‍♂️ FoodDetector\n\n**FoodDetector** is a real-time web-based application for detecting and recognizing Vietnamese dishes using a custom YOLOv10 model trained on the VietFood67 - the **largest** Vietnamese food dataset. This system empowers users with instant nutritional feedback, aiding in dietary awareness and health-conscious decision-making.\n\n---\n\n## ✨ Project Highlights\n\n- Real-time Vietnamese dish detection via images, videos, webcam input and IP camera (RTSP).\n- Nutritional breakdown for each detected dish: Calories, Fat, Saturates, Sugar, Salt.\n- Traffic light system for nutrient awareness.\n- Powered by a custom-trained YOLOv10 model on our largest Vietnamese food image dataset [VietFood67 dataset](https://www.kaggle.com/datasets/thomasnguyen6868/vietfood68).\n- Developed using **Python**, **Streamlit**, and **OpenCV**.\n\n---\n\n## 📚 Publications\n\nThis project has been the foundation of two published research papers:\n\n1. **\"Now I Know What I am Eating: Real-time Tracking and Nutritional Insights Using VietFood67 to Enhance User Experience\"**  \n   🏆 *Best Paper Runner-up Award at SOICT 2024*  \n   🔗 [View Paper](https://link.springer.com/chapter/10.1007/978-981-96-4288-5_35)\n   \n2. **\"It’s Yummy: Real-Time Detection and Recognition of Vietnamese Dishes\"**  \n   📌 *Presented at ICCIT 2024, British University Vietnam (BUV)*  \n   🔗 [View Paper](https://www.igi-global.com/gateway/chapter/380134) \n\n---\n\n## 👨‍💻 Contributors\n\n- **Nguyen Viet Hoang Nam** (Project Lead, Web Developer, YOLOv10 Trainer, VietFood Dataset Gathering)  \n- **Tran Bao Tu** (UI/UX Designer, Poster, Slides Creator)  \n- **Ton That Minh Vu** (Dataset Gathering)  \n- **Dr. Vi Chi Thanh** (Research Supervisor \u0026 Guidance)\n\n---\n\n## 🧠 Technologies Used\n\n| Area             | Tech Stack                        |\n|------------------|-----------------------------------|\n| Model Training   | Python, YOLOv10                   |\n| Deployment       | Streamlit                         |\n| Nutritional Data | Custom JSON + Traffic Light System|\n| Visualization    | Matplotlib, Streamlit Components  |\n\n---\n\n## 📁 Dataset\n\nWe created and released the **VietFood67** dataset for training and evaluation, containing 68 classes (an extra class for human face detection) and 33k images of common Vietnamese dishes with annotated bounding boxes.\n\n📦 [View VietFood67 on Kaggle](https://www.kaggle.com/datasets/thomasnguyen6868/vietfood68)\n\n---\n\n## ⭐ Support This Project\n\nIf you find **FoodDetector** or the **VietFood67** dataset helpful in your research or projects:\n\n- 🌟 Please consider giving this repository a **star** on [GitHub](https://github.com/nvhnam/FoodDetector).\n- 📊 Star the [VietFood67 dataset on Kaggle](https://www.kaggle.com/datasets/thomasnguyen6868/vietfood68) to show your support.\n- 📄 **Cite our papers** in your publications to help us continue our research and development.\n\n\u003e 🆓 The **FoodDetector** and **VietFood67** dataset are free to use for research and educational purposes **with proper citation**. Commercial use or redistribution is **not permitted**.\n\n---\n\n## 🚀 Features\n\n- Upload or stream food media (image, video, webcam, IP camera via RTSP).\n- Real-time detection with bounding boxes and labels.\n- Nutritional values shown per dish and total per meal.\n- User-friendly nutrient traffic light indicators.\n- Designed for low-resource environments (runs without GPU).\n\n---\n\n## 🛠️ Getting Started\n\n\u003e 🚀 **Latest Version:** Please use the [`v2` branch](https://github.com/nvhnam/FoodDetector/tree/v2) before proceeding, as it includes all the newest features and improvements.\n\n### Requirements\n- Python 3.8+\n- Streamlit\n- OpenCV\n- ONNX Runtime\n- Pandas, Numpy, etc.\n\n### Run Locally\n\u003cpre\u003e\ngit clone https://github.com/nvhnam/FoodDetector.git\ncd FoodDetector\ngit checkout v2 \npip install -r requirements.txt\nstreamlit run app.py\n\u003c/pre\u003e\n   \n---\n\n## 📈 Future Work\n\n- 📱 **Mobile App with AR**: Building a mobile version featuring AR overlays that display 3D real-time nutrient values directly on detected dishes.  \n  \u003e 🔍 *Currently seeking passionate collaborators with experience in **Unity** and **AR development** to bring this vision to life! And be the co-author of this new paper.*\n\n- 🧠 Integration with AI nutritionist agents (CrewAI, LangChain) for personalized meal recommendations.\n  \u003e 🔍 *Research is currently in progress.*\n\n- 🏥 Real-time health feedback based on user demographics (age, gender, height, weight, eating patterns).\n- 🍲 Expand the VietFood67 dataset with more regional Vietnamese dishes for greater diversity and recognition accuracy.\n\n\n---\n\n📩 Contact\n\nFor questions or collaborations:\n\n- 📧 Email: nvhnam01@gmail.com\n- 👨‍💻 Portfolio: https://nguyenviethoangnam.vercel.app/\n- 📝 LinkedIn: https://www.linkedin.com/in/nvhnam01/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnvhnam%2Ffooddetector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnvhnam%2Ffooddetector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnvhnam%2Ffooddetector/lists"}