Zhenhua Feng

Centre for Vision, Speech and Signal Processing (CVSSP),

Faculty of Engineering and Physical Sciences,

University of Surrey, Guildford, GU2 7XH, UK

z DOT feng AT surrey DOT ac DOT uk

  • I received my PhD in computer vision and pattern recognition from the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey in 2016. I am currently a research fellow working on the EPSRC FACER2VM (Face Matching for Automatic Identity Retrieval, Recognition, Verification and Management) project at CVSSP, University of Surrey, UK.
  • My research interests include computer vision, machine learning and pattern recognition. I have worked on face recognition and facial image analysis since 2008. My early-stage research is to achieve robust facial landmark detection, using Active Shape Models (ASM), Active Appearance Models (AAM) and their extensions. Now I am focusing on machine-learning-based approaches, such as cascaded shape regression and deep neural networks. My aim is to develop fully automatic face recognition and analysis systems for faces in the wild.
  • I serve as an invited reviewer for the International Journal of Computer Vision, IEEE Trans. on Signal Processing, IEEE Trans. on Multimedia, IEEE Signal Processing Letters, Information Sciences, Pattern Recognition Letters, IET Electronics Letters, IET Image Processing etc.


  • 01-MAR-2018: The paper 'Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks' has been accepted to CVPR2018. [Preprint]
  • 06-DEC-2017: Received the "Departmental Prize for Excellence in Research 2017" from the EEE department of the University of Surrey
  • 20-SEP-2017: Received the "European Biometrics Industry Award 2017" from the European Association for Biometrics (EAB), Darmstadt, Germany
  • 09-SEP-2017: The paper "Gaussian Mixture 3D Mophable Face Model" has been accepted to Pattern Recognition. [ResearchGate]
  • 01-JUN-2017: The paper 'Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild' has been accepted to CVPRW2017, the First Faces-in-the-Wild Workshop-Challenge. [Preprint]
  • 08-MAR-2017: The paper 'Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting' has been accepted to CVPR2017. [Preprint]
  • 17-NOV-2016: The new Google site is online
  • 16-OCT-2016: The Matlab implementation for facial landmark detection and face tracking using supervised descent method (SDM) is online. Please visit my Github webpage for more details.
  • 29-OCT-2015: PaSC Landmarks released: generated 5 and 68 landmarks for the Point and Shoot Face Recognition Challenge (PaSC) dataset


Copyright © 2014-2017 - Zhenhua Feng, University of Surrey.