EYE ASPECT RATIO ADJUSTMENT DETECTION FOR STRONG BLINKING SLEEPINESS BASED ON FACIAL LANDMARKS WITH EYE-BLINK DATASET

<span lang="id">Blink detection is an important technique in a variety of settings, including facial motion analysis and signal processing. However, automatic blink challenging due to its rate. This paper proposes real-time method for detecting eye blinks video series. The based on landmark trained real-world datasets demonstrates robustness against various environmental factors, lighting conditions, emotions, head position. proposed algorithm calculates the position landmarks, extracts scalar values using Eye Aspect Ratio (EAR), characterises proximity each frame. For frame, location vertical distance between eyelids landmark. Blinks are detected by EAR threshold value recognising pattern short temporal window. According results from common data set, it shown that approach more efficient than state-of-the-art techniques.</span>