Facial Landmark Detection Using Generative Adversarial Network Combined with Autoencoder for Occlusion

<div>Exemplar results on COFW. (a) The first row: occluded images under various poses; (b) the secondary row: images under occlusions together with different expressions; and (c) the last row: images occluded by a variety of objects.</div>

Mathematical Problems in Engineering

fig9

Figure 9

Figure 9: Facial Landmark Detection Using Generative Adversarial Network Combined with Autoencoder for Occlusion 