Blink Detection Using Facial Landmark Blink Detector and Multi-Layer Perceptron
Chao‐Lung Chou, Yi-Hsin Huang, Sheng-Chih Ho · 2019
Blink detection is a common face analysis technique that can be applied in disease diagnosis, human-machine interface, biometric anti-spoofing, driver fatigue detection and deception detection. With the advancement of image analysis technology, the facial landmark techniques which support real time analysis have been proposed in recent years. This paper proposes the facial landmark blink detector (FLBD) which uses the facial landmark technique to model the blink behavior. The multi-layer perceptron (MLP) composited with various hidden layers, neurons and activation functions is used as the classifier for training and testing phases in the experiments. Experimental results show the proposed FLBD method with MLP classifier can achieve very high accuracy under the condition that the facial landmarks can be effectively extracted.