Parallel Modelling of Neural Operators for Pattern Recognition -  PAMONOP Network (1994-96)

About

Biologically inspired approaches to machine vision problems were studied in this EU PAMONOP Network (Parallel Modelling of Neural Operators for Pattern Recognition). The problems studied range from motion detection based on insect vision to pattern analysis and optical flow calculation based on complex Gabor filters as a model of the primary cortical image representation in mammalian visual systems. Complex Gabor image representations were studied and applied to set up models of neural operators which are capable of yielding low- and medium-level structural information. Extensive comparative studies will be carried out on alternative methods for effective multi-motion segmentation and representation of face invariants for face representation and recognition. The project involves 9 European partners in which QMW coordinated the UK group including QMW (Gong and Liddell), Cambridge (Daugman) and Sussex (Buxton). Our primary areas of interest are face recognition, optical flow and neural nets. In particular, we addressed the following problems:

Publications

  1. S. McKenna, S. Gong, R. Wurtz, J. Tanner and D. Banin. Tracking facial motion using Gabor wavelets and flexible shape models. In Proc. IAPR International Conference on Audio-Video Based Biometric Person Authentication, pp. 35-43, Crans-Montana, Switzerland, March 1997.
  2. S. McKenna and S. Gong. Non-intrusive person authentication for access control by visual tracking and face recognition. In Proc. IAPR International Conference on Audio-Video Based Biometric Person Authentication, pp. 177-184, Crans-Montana, Switzerland, March 1997.
  3. S. Gong, S. McKenna, and J.J. Collins. An investigation into face pose distributions. In Proc. IEEE International Conference on Automatic Face and Gesture Recognition, pp. 265-270, Killington, Vermont, USA, October 1996.
  4. S. McKenna and S. Gong. Tracking faces. In Proc. IEEE International Conference on Automatic Face and Gesture Recognition, pp. 271-277, Killington, Vermont, USA, October 1996. 
  5. S. McKenna and S. Gong. Combined motion and model-based face tracking. In Proc. British Machine Vision Conference, pp. 755-765, Edinburgh, UK, September 1996.
  6. A. Psarrou, S. Gong and H. Buxton. Modelling spatio-temporal trajectories and face signatures on partially recurrent neural networks. In Proc. IEEE International Conference on Neural Networks, pp. 2226-2232, Perth, Australia, November 1995.
  7. J.J. Collins, S. McKenna and S. Gong. Representation and invariance in face recognition. In Proc. European Workshop on Parallel Modelling of Neural Operators, pp. 9-20, Faro, Portugal, November 1995.
  8. S. McKenna, S. Gong and H. Liddell. Real-time tracking for an integrated face recognition system. In Proc. European Workshop on Parallel Modelling of Neural Operators, pp. 21-27, Faro, Portugal, November 1995.
  9. S. Gong, A. Psarrou, I. Katsoulis and P. Palavouzis. Tracking and recognition of face in image sequences. In Proc. European Workshop on Combined Real and Synthetic Image Processing for Broadcast and Video Production, pp. 97-112, Hamburg, Germany, November 1994.

Partners