Eye state recognition based on shape analysis and fuzzy logic

Eye is the most important feature of human face. Eye state recognition plays an important role in vision based driver fatigue monitoring. A new eye state recognition method based on shape analysis and fuzzy logic is proposed in this paper. Eye characteristic regions are effective segmented by the threshold that synthesized global threshold and local threshold. Then, curvature of the upper eyelid, opening of ellipse fitting eye and proportion of visual pupil are applied to determine eye state in accordance with the rules of fuzzy logic. Experimental results show that the method can recognize eye state quickly, correctly and robustly.