Revision history [back]

I'll try a simple approach, based on this paper [1]:

1. The LBP histogram describing the open eyes is constructed
2. Eye blinks are detected as sharp peaks of the dissimilarity between the template and the histogram of the current frame

[1] Malik, K., & Smolka, B. (2014, April). Eye blink detection using Local Binary Patterns. In Multimedia Computing and Systems (ICMCS), 2014 International Conference on (pp. 385-390). IEEE.

In order to build the LBP histogram of the eyes, you can use these other posts:

• Open eyes / closed eyes in Opencv

  • http://answers.opencv.org/question/30342/open-eyes-closed-eyes-in-opencv/#34509

• how can I align Face Images

  • http://answers.opencv.org/question/24670/how-can-i-align-face-images/#24845

• Facial feature detection

  • http://answers.opencv.org/question/313/facial-feature-detection/#5810

• Facial features detection using haarcascade

  • http://answers.opencv.org/question/5836/facial-features-detection-using-haarcascade/#5901

• Are there any new ways to improve eye detection?

  • http://answers.opencv.org/question/56835/are-there-any-new-ways-to-improve-eye-detection/#56850