{"id":29022892,"url":"https://github.com/michealxq/gesture-recognition-project","last_synced_at":"2026-05-07T02:34:15.102Z","repository":{"id":300715295,"uuid":"1006424543","full_name":"michealxq/gesture-recognition-project","owner":"michealxq","description":"🎯 Real-time Hand Gesture Recognition using MediaPipe and MobileNetV3 (Final Year Project)","archived":false,"fork":false,"pushed_at":"2025-07-02T05:50:39.000Z","size":4345,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-02T06:37:23.552Z","etag":null,"topics":["ai-project","computer-vision","deep-learning","final-year-project","gesture-recognition","mediapipe","mobilenetv3","python","real-time","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/michealxq.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-06-22T08:33:06.000Z","updated_at":"2025-07-02T05:50:42.000Z","dependencies_parsed_at":"2025-06-23T08:35:30.530Z","dependency_job_id":null,"html_url":"https://github.com/michealxq/gesture-recognition-project","commit_stats":null,"previous_names":["michealxq/gesture-recognition-project"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/michealxq/gesture-recognition-project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michealxq%2Fgesture-recognition-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michealxq%2Fgesture-recognition-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michealxq%2Fgesture-recognition-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michealxq%2Fgesture-recognition-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michealxq","download_url":"https://codeload.github.com/michealxq/gesture-recognition-project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michealxq%2Fgesture-recognition-project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32720259,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["ai-project","computer-vision","deep-learning","final-year-project","gesture-recognition","mediapipe","mobilenetv3","python","real-time","tensorflow"],"created_at":"2025-06-26T03:04:05.901Z","updated_at":"2026-05-07T02:34:15.097Z","avatar_url":"https://github.com/michealxq.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Gesture-Controlled Media Player using MediaPipe \u0026 MobileNetV3\nEstimate hand gestures in real-time using MediaPipe and recognize them with a MobileNetV3 model to control a media player application via webcam.\n\n---\n\n## Contents\nThis repository contains:\n- Gesture-controlled media player application (PyQt5 GUI)\n- Real-time webcam hand gesture prediction using MediaPipe\n- MobileNetV3 fine-tuned gesture classification model\n- Demo videos and gesture-action mapping\n- Icons for visual action feedback\n\n---\n\n## Requirements\n- Python 3.8+\n- TensorFlow 2.11+\n- OpenCV 4.5+\n- MediaPipe 0.9+\n- PyQt5\n- VLC Python bindings (`python-vlc`)\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n---\n\n## Demo\nTo launch the gesture-controlled media player with webcam input:\n```bash\npython app.py\n```\n\nEnsure that you have `.mp4` videos inside the `videos/` directory. If no videos are found, the app will exit with an error.\n\n---\n\n## Gesture to Action Mapping\nThe following table lists the recognized gestures and their corresponding media commands:\n\n| Gesture            | Action          | Emoji |\n|--------------------|------------------|--------|\n| Palm               | Play             | ▶️     |\n| Fist               | Pause            | ⏸️     |\n| Call               | Next Video       | ⏭️     |\n| Rock               | Previous Video   | ⏮️     |\n| Like               | Volume Up        | 🔊     |\n| Dislike            | Volume Down      | 🔉     |\n| Two Up             | Skip Forward     | ⏩     |\n| Two Reversed       | Skip Backward    | ⏪     |\n| Stop               | Quit App         | 🛑     |\n\n\n## How it Works\n1. **Hand Detection**: Uses MediaPipe Hands to detect hand landmarks in the webcam frame.\n2. **Cropping \u0026 Preprocessing**: Extracts and pads the hand region, then resizes and normalizes the image for MobileNetV3.\n3. **Gesture Prediction**: Predicts gesture label using the Keras MobileNetV3 model.\n4. **Command Execution**: Maps gesture to media control command (play, pause, volume, etc.) and sends it to VLC.\n5. **UI Feedback**: Displays gesture label, confidence, and corresponding action icon in a PyQt5 GUI.\n\n---\n\n## Model Training (External)\nThis application uses a MobileNetV3 model fine-tuned on a subset of the HaGRID gesture dataset.\nFor training instructions, see the companion notebook:\n- [`notebooks/HaGRID_mobilenetv3_2.ipynb`](notebooks/HaGRID_mobilenetv3_2.ipynb) \n\n---\n\n## Screenshots\n![screenshot](image.png)\n\n---\n\n## License\nThis project is licensed under the MIT License.\n\n---\n\n## Credits\n- Gesture detection powered by [MediaPipe Hands](https://google.github.io/mediapipe/solutions/hands.html)\n- Model architecture: [MobileNetV3-Small](https://arxiv.org/abs/1905.02244)\n- Dataset used for fine-tuning: [HaGRID Dataset](https://paperswithcode.com/dataset/hagrid)\n- VLC integration via [python-vlc](https://pypi.org/project/python-vlc/)\n\n---\n\n\n## Author\n**Ali Ramadan**  \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmichealxq%2Fgesture-recognition-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmichealxq%2Fgesture-recognition-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmichealxq%2Fgesture-recognition-project/lists"}