BossSensor is an experimental open-source application that uses computer vision and machine learning to detect when a specific person, such as a supervisor or manager, approaches a computer workstation. The project uses a webcam to continuously capture images and analyze them using a face classification model trained to distinguish between the designated “boss” and other individuals. When the system detects that the trained face appears in the camera view, the program automatically triggers actions such as hiding the user’s screen or switching to a safe display. The software relies on libraries such as OpenCV, TensorFlow, and Python-based machine learning tools to perform face detection and classification. Training the system requires a dataset of labeled images representing the boss and other people so that the model can learn to differentiate between them.
Features
- Real-time face detection using webcam input
- Machine learning model for recognizing a specific person
- Automatic screen hiding when the target face is detected
- Training scripts for building the face classification model
- Integration with OpenCV and TensorFlow libraries
- Python-based implementation for experimentation and customization