ARCHIVES

In today’s rapidly evolving technological era, ensuring women’s safety remains a significant societal concern, particularly during nighttime and in public spaces. This project presents an intelligent Women Safety System that leverages MediaPipe, OpenCV, and Machine Learning algorithms to provide real-time monitoring and emergency response capabilities. The proposed system detects predefined hand gestures that indicate distress by using MediaPipe for hand tracking and keypoint extraction. Different machine learning models, such as Random Forest, Support Vector Machine, Hybrid Model, and K-Nearest Neighbor, are trained and tested using metrics like Precision, Recall, and F1-score to identify the most effective approach. The system captures live video through a webcam and processes the gestures in real time. When a distress gesture is recognized, it activates an alarm and sends an email along with a captured image to registered contacts or authorities. This ensures timely alerts and enhances the possibility of immediate assistance. By combining computer vision and machine learning, The main goal of this project is to develop a dependable and efficient safety system that supports women and helps create a safer environment.