A method and device for detecting eye blinking

Abstract

The present application discloses a method and device for detecting blinking, the method comprising: obtaining at least a first frame of an eye image, an eye feature of a second frame of an eye image, and the first frame of an eye image representing the opening and closing of the eye image The detection flag of the eye state; based on the detection flag, first judge whether the eye feature of the second frame eye image satisfies the first preset condition relative to the eye feature of the first frame eye image; if so, then judge the second frame eye feature Whether the eye feature of the internal image satisfies the second preset condition; if so, determine that the second frame of the eye image is a blinking state image. It can be seen that according to the essential characteristics of blinking in the blinking process, the upper eyelid moves up and down and the pupil basically does not move, the first preset condition and the second preset condition about blinking are set, based on the eye features in the two frames of eye images before and after Whether the blinking condition is met or not is judged to be in the blinking state, which has good robustness and robustness, reduces detection error rate, and improves detection accuracy.

Description

technical field [0001] The present application relates to the technical field of image recognition and analysis, in particular to a method and device for detecting blinking. Background technique [0002] With the rapid development of biometric information recognition technology and graphic recognition technology, many fields urgently need to perform blink detection based on image processing technology, such as virtual reality (English: Virtual Reality, abbreviation: VR) field, augmented reality (English: Augmented Reality, abbreviation : AR), artificial intelligence, etc. [0003] In the prior art, eye blink detection is generally performed by means of simple threshold judgment or logic judgment based on the eye image, for example, judging whether the eye center is in the current communication area or not. However, the inventor has found through research that the current various judgment methods for realizing blink detection do not capture the essence of blinking, and it is...

AI Technical Summary

Problems solved by technology

However, the inventors have found through research that the current various judgment methods for realizing blink detection do not capture the essence of blinking, and it is difficult to capture the real blinking moment, especially when the frame rate is not high, it is even more difficult to capture the entire blinking process. , prone to detection errors

Images