期刊
COGNITIVE COMPUTATION
卷 14, 期 3, 页码 1123-1139出版社
SPRINGER
DOI: 10.1007/s12559-021-09846-5
关键词
Face alignment; Facial landmark detection; Multistage model; Spatial transformer generative adversarial networks; Stacked hourglass networks; Exemplar-based shape constraints
资金
- National Natural Science Foundation of China [61372 137]
- Natural Science Foundation of Anhui Province [1908085MF209, 1708085MF151]
- Natural Science Foundation for the Higher Education Institutions of Anhui Province [KJ2019A0036]
This paper proposes a multistage model based on deep neural networks for face alignment, utilizing spatial transformer networks, hourglass networks, and exemplar-based shape constraints to address initialization issues and improve performance in challenging conditions such as rotation and scale variations. Experimental results demonstrate the superior performance of the proposed method over other state-of-the-art methods on challenging benchmark datasets.
The ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer-generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据