Face Description with Local Binary Patterns: Application to Face Recognition
Outline
Introduction
LBP
Uniform LBP
Face description using LBP
Dataset
Results
MLBP and Staggered MLBP
Conclusion
References

Introduction
Key issue is face analysis  finding efficient descriptor for face appearance

Holistic methods  Principal component Analysis (PCA), Linear Discriminant Analysis (LDA), and 2D PCA

Local region methods 
A facial image representation based on Local Binary Pattern (LBP) texture features from local facial regions.
Strengths : Highly discriminative – invariance to monotonic gray-level changes – computationally efficient