Joint Subspace and Low-Rank Coding Method for Makeup Face Recognition

Facial makeup significantly changes the perceived appearance of face and reduces accuracy recognition. To adapt to application smart cities, in this study, we introduce a novel joint subspace low-rank coding method for exploit more discriminative information images, use feature projection technology find proper learn dictionary such subspace. In addition, constraint learning. Then, design learning framework iterative optimization strategy obtain all parameters simultaneously. Experiments on real-world dataset achieve good performance demonstrate validity proposed method.