A survey to analyze the mainstream and future face alignment algorithms

Abstract

Face Alignment, focusing on detecting facial landmarks of input faces, has been widely applied in criminal investigation and security verification system. However, face alignment keeps an incredibly challenging task in computer version due to occlusion, pose variation and unsuited initial shape. Many related methods have been proposed to tackle these problems. Many traditional methods, such as Face Alignment by Coarse-to-Fine Shape Searching, focus on initial face shape optimization. Recent studies pay more attention to making advantages of deep learning approaches such as cascaded classifiers, convolutional neural networks and multitask learning methods, which have already achieved outstanding performance on prevalent datasets. In this paper, we summarize the mainstream face alignment models and analyze the corresponding advantages and shortages. Then, we also discuss further application and development of face alignment algorithms in the future.