[深度学习论文笔记][Face Recognition] DeepFace: Closing the Gap to Human-Level Performance in Face Verificati

Taigman, Yaniv, et al. “Deepface: Closing the gap to human-level performance in face verification.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014. (Citations: 851).

1 Motivation

Aligning faces in the unconstrained scenario is difficult because the variations of
• Pose (due to the non-planarity of the face).
• Non-rigid expressions.

The whole detection and alginment pipeline can be seen in Fig. 12.

Figure 12: Detection and alginment pipeline. (a) The detected face, with 6 initial fiducial points. (b) The induced 2D-aligned crop. (c) 67 fiducial points on the 2D-aligned crop with their corresponding Delaunay triangulation, we added triangles on the contour to avoid discontinuities.