Silent Alert: Advancing Women's Security through Smart Sign Recognition and AI

In today's world, many technologically innovative solutions are developed to prioritize women's safety solutions, especially during nighttime. This research's main aim is to focus on addressing crucial safety issues like emergencies and harassment in public spaces. To build an efficient model the proposed system uses technologies like MediaPipe and machine learning algorithms like random forest, decision tree, support vector machine (SVM), gaussian naive bayes, k-nearest neighbor (KNN), gradient boosting and stacking classifier (hybrid model). Rigorous testing ensures the selection of the most effective model, assessed through metrics like F1 score, precision, and recall. By integrating technology and machine learning, apart from raising awareness and fostering safe environments the proposed work also aims to empower women and enhance their safety. MediaPipe significantly enhances the accuracy of sign language recognition and also plays a vital role in improving the system's effectiveness. At the same time, OpenCV enables real-time video capture for comparison with the trained model. To enhance the system, predictions are made based on the recognized sign language gestures. In the system, predictions are improved by analyzing recognized sign language gestures. It also incorporates a database matching system that activates an alarm and sends a mail with a screenshot upon detecting predefined gestures. This function ensures prompt notifications, enabling authorities to respond promptly to identified incidents concerning women's safety. The system's ability to instantly recognize and react to specific gestures makes it an effective tool for addressing safety issues for women.