Face Alignment by Coarse‐to‐Fine Shape Estimation. Issue 6 (1st November 2018)

• Record Type: Journal Article
• Authors: Wan, Jun; Li, Jing; Chang, Jun; WU, Yujia; Xiao, Yafu; Song, Chengfang
• Is Part Of: Chinese journal of electronics. Volume 27:Issue 6(2018)
• Page Start: 1183
• Page End: 1191
• Publication Date: 2018-11-01
• Subjects: Facial appearance attributes -- Head pose classification model -- Convolutional neural network -- Initialized shape -- Cascaded regression; face recognition -- feedforward neural nets -- image classification -- pose estimation -- regression analysis; face alignment -- Coarse‐to‐fine shape estimation -- facial expressions -- estimated facial appearance attributes -- initialized shape -- ground‐truth shape -- head pose classification -- convolutional neural network -- cascaded regression; Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2018.09.014
• Languages: English
• ISSNs: 1022-4653

Abstract

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.