Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild

被引:22
|
作者
Feng, Zhen-Hua [1 ,2 ]
Kittler, Josef [1 ]
Awais, Muhammad [1 ]
Huber, Patrik [1 ]
Wu, Xiao-Jun [2 ]
机构
[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 7XH, Surrey, England
[2] Jiangnan Univ, Sch Internet Things Engn, Wuxi 214122, Peoples R China
基金
英国工程与自然科学研究理事会;
关键词
D O I
10.1109/CVPRW.2017.262
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a framework for robust face detection and landmark localisation of faces in the wild, which has been evaluated as part of 'the 2nd Facial Landmark Localisation Competition'. The framework has four stages: face detection, bounding box aggregation, pose estimation and landmark localisation. To achieve a high detection rate, we use two publicly available CNN-based face detectors and two proprietary detectors. We aggregate the detected face bounding boxes of each input image to reduce false positives and improve face detection accuracy. A cascaded shape regressor, trained using faces with a variety of pose variations, is then employed for pose estimation and image pre-processing. Last, we train the final cascaded shape regressor for fine-grained landmark localisation, using a large number of training samples with limited pose variations. The experimental results obtained on the 300W and Menpo benchmarks demonstrate the superiority of our framework over state-of-the-art methods.
引用
收藏
页码:2106 / 2111
页数:6
相关论文
共 50 条
  • [1] Face Detection, Pose Estimation, and Landmark Localization in the Wild
    Zhu, Xiangxin
    Ramanan, Deva
    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 2879 - 2886
  • [2] An Efficient Model for Simultaneous Face Detection, Pose Estimation and Landmark Localisation
    Hung Thanh Vu
    Mai Vuong Minh Nhat
    Bac Le
    2015 Seventh International Conference on Knowledge and Systems Engineering (KSE), 2015, : 13 - 18
  • [3] Robust Landmark Selection for 3D Face Pose Estimation
    Civir, Cevdet
    Topal, Cihan
    2019 27TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2019,
  • [4] Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion
    Wu, Yue
    Gou, Chao
    Ji, Qiang
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5719 - 5728
  • [5] Learning the Face Shape Models for Facial Landmark Detection in the Wild
    Wu, Yue
    Ji, Qiang
    FACE AND FACIAL EXPRESSION RECOGNITION FROM REAL WORLD VIDEOS, 2015, 8912 : 33 - 45
  • [6] Joint Estimation of Pose and Face Landmark
    Lee, Donghoon
    Chung, Junyoung
    Yoo, Chang D.
    COMPUTER VISION - ACCV 2014, PT IV, 2015, 9006 : 305 - 319
  • [7] Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation
    Lee, Yongju
    Jang, Sungjun
    Bae, Han Byeol
    Jeon, Taejae
    Lee, Sangyoun
    SENSORS, 2024, 24 (10)
  • [8] Stacked Hourglass Network for Robust Facial Landmark Localisation
    Yang, Jing
    Liu, Qingshan
    Zhang, Kaihua
    2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 2025 - 2033
  • [9] Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces
    Iranmanesh, Seyed Mehdi
    Dabouei, Ali
    Soleymani, Sobhan
    Kazemi, Hadi
    Nasrabadi, Nasser M.
    2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 319 - 329
  • [10] Constrained Local Neural Fields for robust facial landmark detection in the wild
    Baltrusaitis, Tadas
    Robinson, Peter
    Morency, Louis-Philippe
    2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2013, : 354 - 361