Locality-constrained framework for face alignment

作     者：Jie ZHANG Xiaowei ZHAO Meina KAN Shiguang SHAN Xiujuan CHAI Xilin CHEN 

作者机构：Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Alibaba Group Hangzhou 311121 China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2019年第13卷第4期

页      面：789-801页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：the National Natural Science Foundation of China (Grant Nos. 61650202, 61402443, 61672496) the Strategic Priority Research Program of the CAS (XDB02070004) 

主　　题：locality-constrained AAM locality-constrained DFM face alignment sparsity-regularization 

摘      要：Although the conventional active appearance model (AAM) has achieved some success for face alignment, it still suffers from the generalization problem when be applied to unseen subjects and images. To deal with the gem eralization problem of AAM, we first reformulate the original AAM as sparsity-regularized AAM, which can achieve more compact/better shape and appearance priors by selecting nearest neighbors as the bases of the shape and appearance model. To speed up the fitting procedure, the sparsity in sparsity?regularized AAM is approximated by using the locality (i.e., AT-nearest neighbor), and thus inducing the locality-constrained active appearance model (LC-AAM). The LC-AAM solves a constrained AAM-like fitting problem with the K-nearest neighbors as the bases of shape and appearance model. To alleviate the adverse influence of inaccurate AT-nearest neighbor results, the locality constraint is further embedded in the discriminative fitting method denoted as LC-DFM, which can find better K-nearest neighbor results by employing shape-indexed feature, and can also tolerate some inaccurate neighbors benefited from the regression model rather than the generative model in AAM. Extensive experiments on several datasets demonstrate that our methods outperform the state-of-the-arts in both detection accuracy and generalization ability.