Eyeglasses fisherfaces based glasses-face recognition
ABSTRACT In this paper, a novel glasses-face recognition approach eyeglasses fisherfaces, is proposed to recognize glasses-face, which treats eyeglasses as a feature of facial image, and applies fisherfaces into glasses-face images. It overcomes the choke point of removing eyeglasses which be used in previous glasses-face recognition methods. Considering the instability of eyeglasses as a facial feature, here we make use of 3D face synthesis method based on genetic algorithm to reconstruct virtual samples, to enrich the sample library. It not only can be used in different pose, illumination and expression, but also provide a new thought-way for occlusion problem in face recognition. On CASPEAL face databases, our experimental results demonstrate that eyeglasses fisherfaces performs well.
- [show abstract] [hide abstract]
ABSTRACT: Due its possibilities in security systems and robotics, face recognition is one of the most researched areas within the biometric field. In a common scenario from real life face recognition problem, the dimension in the sample space is larger than the number of training samples per class. This is known as the “small sample size problem”. Discriminative Common Vectors (DCV) technique has been used to face this problem successfully. In this paper, we introduce a new approach based on DCV theory to increase its performance in face verification tasks. This modification uses a specific set of projecting vectors selected by an optimization algorithm based on the classifier's performance, and in the fact that no such thing as common vectors exists when this set contains vectors from the range of the within-class scattering matrix (SW ). Based on these two ideas, we may call this approach Discriminative Multi-Projection Vectors (DMPV) as it projects samples in both range and null space of SW. We tested the system with different databases and results show that DMPV outperforms classic DCV method.01/2010;