How althafshaik15/gesturecontrol works
GestureControls is a webcam-driven desktop gesture-control application. Its workflow captures frames, detects and annotates hands, classifies landmarks, maps gestures to desktop actions, and displays a live HUD. The controller also supports scrolling, clicks, volume, brightness, screenshots, and media playback. The README is empty, so this map relies on the supplied source; external integrations are shown only where those files invoke them.
Main entry points: controller.py Gesture Controller · main.py App Loop and HUD · gesture_detector.py Hand Detector · gesture_classifier.py Gesture Classifier
Components 13
Application Runtime
- App Loop and HUD
main.py
Hand Vision
- Hand Detector
gesture_detector.py
Gesture Recognition
- Gesture Classifier
gesture_classifier.py - Gesture Config
config.py
Desktop Actions
- Gesture Controller
controller.py
Other components
- User
- OpenCV
- Webcam
- MediaPipe Hands
- Desktop Input
- Windows Audio
- Screen Brightness
- Media Keys
Connections 15
- User → Webcam: shows gestures
- App Loop and HUD → OpenCV: captures and displays
- Webcam → OpenCV: provides frames
- App Loop and HUD → Hand Detector: processes frames
- Hand Detector → OpenCV: converts frames
- Hand Detector → MediaPipe Hands: detects hands
- Hand Detector → App Loop and HUD: returns landmarks
- App Loop and HUD → Gesture Classifier: classifies landmarks
- Gesture Classifier → Gesture Config: reads thresholds and indices
- App Loop and HUD → Gesture Controller: dispatches gesture
- Gesture Controller → Gesture Config: reads control settings
- Gesture Controller → Desktop Input: moves, clicks, scrolls, screenshots
- Gesture Controller → Windows Audio: adjusts volume
- Gesture Controller → Screen Brightness: raises brightness
- Gesture Controller → Media Keys: sends play/pause