Face recognition with local steerable phase feature

In this paper, we propose a novel local steerable phase (LSP) feature extracted from the face image using steerable filters for face recognition. The new type of local feature is semi-invariant under common image deformations and distinctive enough to provide useful identity information. Phase information provided by steerable filters is locally stable with respect to scale changes, noise and brightness changes. Phase features from multiple scales and orientations are concatenated to an augmented feature vector which is used to evaluate similarity between face images. We use a nearest-neighbor classifier based on the local weighted phase-correlation for final classification. The experimental results on FERET dataset show an encouraging recognition performance.