Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces

被引:0
|
作者
Iranmanesh, Seyed Mehdi [1 ]
Dabouei, Ali [1 ]
Soleymani, Sobhan [1 ]
Kazemi, Hadi [1 ]
Nasrabadi, Nasser M. [1 ]
机构
[1] West Virginia Univ, Morgantown, WV 26506 USA
关键词
ALIGNMENT; NETWORK;
D O I
10.1109/wacv45572.2020.9093508
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we present a practical approach to the problem of facial landmark detection. The proposed method can deal with large shape and appearance variations under the rich shape deformation. To handle the shape variations we equip our method with the aggregation of manipulated face images. The proposed framework generates different manipulated faces using only one given face image. The approach utilizes the fact that small but carefully crafted geometric manipulation in the input domain can fool deep face recognition models. We propose three different approaches to generate manipulated faces in which two of them perform the manipulations via adversarial attacks and the other one uses known transformations. Aggregating the manipulated faces provides a more robust landmark detection approach which is able to capture more important deformations and variations of the face shapes. Our approach is demonstrated its superiority compared to the state-of-the-art method on benchmark datasets AFLW, 300-W, and COFW.
引用
收藏
页码:319 / 329
页数:11
相关论文
共 50 条
  • [31] Robust Facial Landmark Detection under Significant Head Poses and Occlusion
    Wu, Yue
    Ji, Qiang
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 3658 - 3666
  • [32] 2.5D Cascaded Regression for Robust Facial Landmark Detection
    Xu, Jinwen
    Zhao, Qijun
    Li, Xiaofeng
    Wang, Yang
    2017 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB), 2017, : 124 - 132
  • [33] Towards Accurate Facial Landmark Detection via Cascaded Transformers
    Li, Hui
    Guo, Zidong
    Rhee, Seon-Min
    Han, Seungju
    Han, Jae-Joon
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 4166 - 4175
  • [34] Detection of AI-Manipulated Fake Faces via Mining Generalized Features
    Yu, Yang
    Ni, Rongrong
    Li, Wenjie
    Zhao, Yao
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 18 (04)
  • [35] ROBUST AND EFFICIENT FACIAL LANDMARK LOCALIZATION
    Hu, Hong
    Wang, Chen
    Jiang, Tao
    Guo, Zhixian
    Han, Yonggang
    2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2021,
  • [36] Landmark-in-facial-component: Towards occlusion-robust facial landmark localization
    Li, Xiaoqiang
    Wu, Kaiyuan
    Zhang, Shaohua
    Image and Vision Computing, 2024, 151
  • [37] Summary on Facial Landmark Detection
    Wen, Jinghao
    PROCEEDINGS OF THE 2017 2ND INTERNATIONAL CONFERENCE ON MACHINERY, ELECTRONICS AND CONTROL SIMULATION (MECS 2017), 2017, 138 : 253 - 259
  • [38] FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos
    Sun, Keqiang
    Wu, Wenyan
    Liu, Tinghao
    Yang, Shuo
    Wang, Quan
    Zhou, Qiang
    Ye, Zuochang
    Qian, Chen
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5461 - 5470
  • [39] Robust FEC-CNN: A High Accuracy Facial Landmark Detection System
    He, Zhenliang
    Zhang, Jie
    Kan, Meina
    Shan, Shiguang
    Chen, Xilin
    2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 2044 - 2050
  • [40] Robust facial landmark detection for three-dimensional face segmentation and alignment
    Wu, Hai Shan
    Chen, Yan Qiu
    JOURNAL OF ELECTRONIC IMAGING, 2010, 19 (03)