Zhenhua Feng's personal webpage

z DOT feng AT surrey DOT ac DOT uk Centre for Vision, Speech and Signal Processing (CVSSP), Faculty of Engineering and Physical Sciences, University of Surrey, Guildford, GU2 7XH, UK

• About me

I am currently a research fellow at the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK, working on the EPSRC project FACER2VM (Face Matching for Automatic Identity Retrieval, Recognition, Verification and Management). I received my PhD from the University of Surrey on computer vision and pattern recognition in 2016.

My research interests include computer vision, machine learning and pattern recognition. I have worked on face recognition and facial image analysis since 2008. My aim is to develop fully automatic face recognition and analysis systems for faces in the wild. Please go to our project webpage for more details.

I have served as an invited reviewer for many international journals and conference proceedings, such as IEEE Trans. on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, IEEE Trans. on Sigianl Processing, IEEE Trans. on Image Processing, IEEE Trans. on Multimedia, IEEE Signal Processing Letters, Information Sciences, Pattern Recofnition, Pattern Recognition Letters, IET Electronics Letters etc.

• News

• The paper `Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks' has been accepted to CVPR 2018. [ Link ]
• Received the "Departmental Prize for Excellence in Research 2017" from the Department of Electrical and Electronic Engineering, University of Surrey.
• Received the "European Biometrics Industry Award 2017" from the European Association for Biometrics (EAB), Darmstadt, Germany.
• The paper `Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting' has been accepted to CVPR 2017.
• The Matlab implementation for facial landmark detection and tracking using supervised descent method (SDM) is online. Please visit my Github webpage for more details. The source code of my RCRC and CCR will be online soon.

• Publications ( Google Scholar )

  • 2018

    • Robust Pedestrian Detection for Semi-automatic Construction of A Crowded Person Re-Identification Dataset
      Zengxi Huang, Zhen-Hua Feng, Fei Yan, Josef Kittler and Xiao-Jun Wu
      International Conference on Articulated Motion and Deformable Objects (AMDO2018), Palma de Mallorca, Spain, 2018.
    • Dictionary Integration using 3D Morphable Face Models for Pose-invariant Collaborative-representation-based Classification
      Xiaoning Song, Zhen-Hua Feng, Guosheng Hu, Josef Kittler, William Christmas and Xiao-Jun Wu
      IEEE Transactions on Information Forensics and Security, Vol. 13(11), 2018, pp:2734-2745.
      [ Preprint ]
    • Evaluation of Dense 3D Reconstruction from 2D Face Images in the Wild
      Zhen-Hua Feng, Patrik Huber, Josef Kittler, Peter Hancock, Xiao-Jun Wu, Qijun Zhao, Paul Koppen, Matthias Rätsch
      IEEE International Conference on Face and Gesture Recognition (FG2018), Xian, China, 2018.
      [ Preprint ]
    • Advances in Facial Landmark Detection
      Zhen-Hua Feng, Josef Kittler
      Biometric Technology Today, Vol. 3, 2018, pp: 8-11.
      [ DOI ]
    • Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
      Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber and Xiao-Jun Wu
      IEEE International Conference on Computer Vision and Pattern Recognition (CVPR2018), Salt Lake City, USA, 2018.
      [ Preprint ]
    • Gaussian Mixture 3D Morphable Face Model
      Paul Koppen, Zhen-Hua Feng, Josef Kittler, Muhammad Awais, William Christmas, Xiao-Jun Wu and He-Feng Yin
      Pattern Recognition, Vol. 74, 2018, pp: 617-628.
      [ Preprint ] [ DOI ]

  • 2017

    • Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild
      Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber and Xiao-Jun Wu
      IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW2017）, Honolulu, Hawaii, USA, 2017.
      [ arXiv ] [ Preprint ] [ DOI ]
    • Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting
      Zhen-Hua Feng, Josef Kittler, William Christmas, Patrik Huber and Xiao-Jun Wu
      IEEE International Conference on Computer Vision and Pattern Recognition (CVPR2017）, Honolulu, Hawaii, USA, 2017.
      [ arXiv ] [ Preprint ]
    • Efficient 3D Morphable Face Model Fitting
      Guosheng Hu, Fei Yan, Josef Kittler, William Christmas, Chi Ho Chan, Zhen-Hua Feng, Patrik Huber
      Pattern Recognition, Vol. 67, 2017, pp:366-379
      [ DOI ] [ Preprint ]
    • Dynamic Dictionary Optimization for Sparse-representation-based Face Classification using Local Difference Images
      Changbin Shao, Xiaoning Song, Zhen-Hua Feng, Xiao-Jun Wu, Yuhui Zheng
      Information Sciences Vol. 393, 2017, pp:1-14.
      [ DOI ] [ Preprint ]
    • Half-Face Dictionary Integration for Representation-Based Classification
      Xiaoning Song, Zhen-Hua Feng, Guosheng Hu, Xiaojun Wu
      IEEE Transactions on Cybernetics Vol.47(1), 2017, pp:142-152
      [ DOI ] [ Preprint ]

  • 2016

    • A Unified Tensor-based Active Appearance Face Model
      Zhen-Hua Feng, Josef Kittler, William Christmas and Xiao-Jun Wu
      arXiv preprint arXiv:1612.09548, 30/12/2016. [ Preprint ]
    • 3D Morphable Face Models and Their Applications
      Josef Kittler, Patrik Huber, Zhenhua Feng, Guosheng Hu, William Christmas
      International Conference on Articulated Motion and Deformable Objects (AMDO2016), 185-206, Palma de Mallorca, Spain, 2016
      [ bibtex ] [ DOI ] [ Preprint ]
    • Towards multi-scale fuzzy sparse discriminant analysis using local third-order tensor model of face images
      Xiaoning Song, Zhenhua Feng, Xibei Yang, Xiaojun Wu, Jingyu Yang
      Neurocomputing, Vol.185, 2016, pp: 53-63
      [ bibtex ] [ DOI ]

  • 2015

    • Cascaded Collaborative Regression for Robust Facial Landmark Detection Trained Using a Mixture of Synthetic and Real Images With Dynamic Weighting
      Zhenhua Feng, Gguosheng Hu, Josef Kittler, William Christmas, Xiao-Jun Wu
      IEEE Transactions on Image Processing, Vol.24(11), 2015, pp:3425-3440
      [ bibtex ] [ Preprint ]
    • Random Cascaded-Regression Copse for Robust Facial Landmark Detection.
      Zhenhua Feng, Patrik Huber, Josef Kittler, William Christmas, Xiao-Jun Wu
      IEEE Signal Processing Letters, Vol.22(1), 2015, pp:76-80
      (Accepted as the cover paper of IEEE SPL, and recognised as part of the "top 10%" papers by ICIP2015.)
      [ bibtex ] [ Preprint ] [ Landmarks for the PaSC dataset ]
    • Progressive sparse representation-based classification using local discrete cosine transform evaluation for image recognition
      Xiaoning Song, Zhenhua Feng, Guosheng Hu, Xibei Yang, Jingyu Yang, Yunsong Qi
      Journal of Electronic Imaging, Vol.24(5), 053010 [ bibtex ] [ DOI ]
    • Fitting 3D Morphable Models using Local Features.
      Patrik Huber, Zhenhua Feng, William Christmas, Josef Kittler, Matthias Rätsch
      IEEE International Conference on Image Processing （ICIP2015）, 1195-1199, Quebec City, Canada, 2015
      (Recognised as part of the "top 10%" papers by ICIP2015.)
      [ bibtex ] [ Preprint ] [ Code ]

  • 2013

    • Feature Level Multiple Model Fusion Using Multilinear Subspace Analysis with Incomplete Training Set and Its Application to Face Image Analysis.
      Zhenhua Feng, Josef Kittler, William Christmas, Xiao-Jun Wu
      International Workshop on Multiple Classifier Systems (MCS2013)), 73-84, Nanjing, China, 2013
      [ bibtex ] [ Preprint ]

  • 2012

    • An Improved AAM Method for Extracting Human Facial Features.
      Tao Zhou, Xiao-Jun Wu, Tao Wu, Zhenhua Feng
      Journal of Applied Mathematics, Article ID 643562, 2012
      [ bibtex ] [ Preprint ]
    • Automatic face annotation by multilinear AAM with Missing Values.
      Zhenhua Feng, Josef Kittler, William Christmas, Xiao-Jun Wu, Sebastian Pfeiffer
      IEEE/IAPR International Conference on Pattern Recognition, 2586-2589, Tsukuba Science City, Japan, 2012
      [ bibtex ] [ Preprint ]

• Links

  • WiKiCFP: A Wiki for Calls for Papers. http://www.wikicfp.com/cfp/
  • Face++: A face recognition company - has free Andriod, IOS and Matlab SDK for face detection, landmarking, gender classification and age estimation. http://www.faceplusplus.com.cn/
  • UFLDL: Unsupervised Feature Learning and Deep Learning - from Andrew NG, Stanford. http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial/
  • VLFEAT: A open source library with popular computer vision algorithms in Matlab and C. http://www.vlfeat.org/index.html

Copyright: © 2014-2015 Zhenhua FENG · University of Surrey