The invention discloses a blink detection method based on an eye contour feature point aspect ratio, and the method comprises the steps: obtaining a video stream, and extracting a single-frame face image set from the video stream; Extracting a face rectangular frame in the face image from the single-frame face image set by using a deep neural network, and obtaining a face rectangular frame coordinate; Obtaining eye key point coordinates in the single-frame face image set according to the face rectangular frame coordinates; Calculating the eye aspect ratio of the single-frame face image set according to the eye key point coordinates so as to judge whether blinking occurs or not according to the eye aspect ratio. According to the method, whether blinking occurs or not is judged by calculating the double-eye aspect ratio, the influence of light intensity, character postures and the like on blinking judgment can be overcome, high robustness is achieved, and the method is simple in calculation, high in precision, high in efficiency and capable of being better applied to the fields of living body recognition, fatigue driving monitoring and the like.