Face alignment by coarse-to-fine shape estimation

Abstract

This paper presents a way to face alignment by Coarse-to-fine shape estimation (CFSE). Head poses, facial expressions and other facial appearance attributes are estimated coarsely as well as the main landmarks will be detected. The entire shape will be further estimated. This paper constructs an independent Head pose classification (HPC) model based on convolutional neural network to estimate and classify head poses. With the classification result, the estimated facial appearance attributes and the detected landmarks, a more accurate shape will be constructed. That shape will be used as the initialized shape and optimized by cascaded regression to approximate the ground-truth shape. Experiments on two challenging database demonstrate that CFSE outperforms the state-of-the-art methods.