eye-state-classification

Real-time driver drowsiness detection system using MobileNet transfer learning, TensorFlow/Keras, OpenCV, and Streamlit with WebRTC-based live video streaming and inference for enhanced road safety.

Binary image classification (Awake vs Sleepy) using deep learning on infrared eye images from the MRL Eye Dataset (~85K images). Built with transfer learning for real-time drowsiness detection.

Reproducible evaluation of an eye-state + temporal-alerting drowsiness pipeline, with subject-disjoint testing, baselines, failure analysis and oracle decomposition.

EN: Eye state classification training and ONNX export for Blink Call, recognizing closed, open, and unknown inputs for robust blink-based interaction. || 中文：Blink Call 的眼部状态分类训练与 ONNX 导出项目，识别闭眼、睁眼和无关输入，为眨眼交互提供模型支持。