Dr. David Windridge
|
| |||||
|
|
Introduction
My research interests are in the areas of Cognitive Systems, Pattern Recognition and Statistical Image Processing (the latter deriving from a previous research interest in Observational Cosmology).
Recent Research Collaborations
2009-2013: ACASVA EPSRC Foresight Grant (acting as Project Coordinator)
2007-2010: DIPLECS (co-investigator, EU framework 7) Dynamic Interactive Perception-Action Learning in Cognitive Systems
2004-2007: COSPAL (EU framework 6) Cognitive Systems using Perception-Action Learning
2005-2007: PRINCESS (INTAS) Principles of Dissimilarity-Based Pattern Recognition in Signals and Symbolic Sequences
2004-2005: VAMPIRE (EU framework 5) Visual Active Memory Processes and Interactive Retrieval
2002-2004: COGVISYS (EU framework 5) Cognitive Vision Systems
2001-2004: Stochastic Vector Quantisation Framework Classifier Fusion (as Principle Investigator - in collaboration with QinetiQ)
Ph.D. Supervision
Current Students:
Affan Shaukat
Aftab Khan
Debaditya Goswami
Former Students:
Gergely Rakoczi (Erasmus exchange)
Mikhail Schevchenko
Robin Patenall
Papers Outlining Main Methodological Contributions
1
D. Windridge and Josef Kittler,
A Morphologically Optimal Strategy for Classifier Combination,
Indicative Publications
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 25, no. 3, March 2003, pp. 343-353
link
pdf
2
David Windridge,
Morphologically Debiased Classifier Fusion: A Tomography-Theoretic Approach,
Advances in Imaging and Electron Physics, vol 134, 2005, Elsevier Academic Press
(A detailed account of the above technique as a method for removing morphological bias commissioned by Elsevier)
link
pdf
3
D. Windridge and R. Bowden,
Hidden Markov chain estimation and parameterisation via ICA-based feature-selection,
Pattern Analysis & Applications, July 2005, vol. 8, pp 115-124,
Publisher: Springer-Verlag London Ltd
link
pdf
4
D. Windridge and S. Phillipps, A Fluctuation Analysis for Optical
Cluster Galaxies - I Theory,
MNRAS
(Mon. Not. Roy. Astron. Soc), 319, p. 591, 11/2000
(A stochastic technique for dark-matter detection)
link
pdf
5
D. Windridge and J. Kittler, Epistemic Constraints on Autonomous Symbolic Representation in Natural and Artificial Agents,
Applications of Computational Intelligence in Biology: Current Trends and Open Problems, Studies in Computational Intelligence (SCI),
vol(122), 2008, Springer, ISBN: 978-3-540-78533-0
(A philosophical exposition on the limits to self-updating cognitive representation arising from the earlier survey of mechanisms for Cognitive Bootstrapping)
link
pdf
6
D. Windridge and J. Kittler, Perception-Action Learning as an
Epistemologically-Consistent Model
for Self-Updating Cognitive
Representation,
Brain Inspired Cognitive Systems (special
issue), Advances in Experimental Medicine and Biology 657, 2010,
DOI 10.1007/978-0-387-79100-5_6, Springer-Verlag, New York
(An application of the above ideas, demonstrating the practical performance benefits)
pdf
7
Mikhail Shevchenko, David Windridge and Josef Kittler,
A Linear-Complexity Reparametrisation Strategy for the Hierarchical Bootstrapping of Capabilities within Percept-Action Architectures,
Image and Vision Computing, 27, 2009, pp 1702-1714
link
pdf
(Book chapters, Journal Papers, Conference papers, Technical reports, Theses)
[45] Alexander Tatarchuk, Valentina Sulimova, David Windridge, Vadim Mottl,
Supervised Selective Combining Pattern Recognition Modalities and its Application to Signature Verification by Fusing On-Line and Off-Line Kernels,
8th International Workshop on Multiple Classifier Systems MCS 2009, Reykjavik, 2009.
[44] D. Windridge, N. Poh, V. Mottl, A. Tatarchuk, A. Eliseyev,
Handling Multimodal Information Fusion with Missing Observations Using the Neutral Point Substitution Method,
8th International Workshop on Multiple Classifier Systems MCS 2009, Reykjavik, 2009.
[43] Mikhail Shevchenko, David Windridge and Josef Kittler,
A Linear-Complexity Reparametrisation Strategy for the Hierarchical Bootstrapping of Capabilities within Percept-Action Architectures,
Image and Vision Computing, 27, 2009, pp 1702-1714
[42] David Windridge and Josef Kittler,
Active Perception-Action Learning in the Relational Domain via
Cognitive Bootstrapping
Special issue of the BICS proceedings (accepted)
[41] D. Windridge, V. Mottl, A. Tatarchuk, A. Eliseyev,
Selectivity Supervision in Combining Pattern-Recognition Modalities
by Feature- and Kernel-Selective Support Vector Machines
Proc. 19th International Conference of Pattern Recognition, ICPR 2008, Florida, USA
[40] David Windridge, Debaditya Goswami, Josef Kittler,
Subsurface Scattering Deconvolution for Improved NIR-Visible Facial Image Correlation,
Proc. of 8th IEEE International Conference on Automatic Face and Gesture Recognition, 2008
[39] David Windridge, Josef Kittler,
A model for empirical validation in self-updating cognitive representation,
Proceedings of Brain Inspired Systems 2008 (BICS 2008), Sao Luis, Brazil, 2008
[38] David Windridge, Mikhail Shevchenko, Josef Kittler
An Entropy-Based Approach to the Hierarchical Acquisition of Perception-
Action Capabilities
Proc. of 4th International Cognitive Vision Workshop ICVW 2008,
(6th International Conference on Computer Vision Systems ICVS 2008), Santorini, Greece, 2008
[37] Article relating to the DIPLECS project arising from an interview I gave to the The Engineer magazine:
http://www.theengineer.co.uk/Articles/305811/Away+from+engineering.htm
link
[36] D. Windridge and Josef Kittler,
Epistemic Constraints on Autonomous Symbolic Representation in Natural and Artificial Agents,
Applications of Computational Intelligence in Biology: Current Trends and Open Problems,
Studies in Computational Intelligence (SCI),
vol(122), 2008, Springer, ISBN: 978-3-540-78533-0
[35] D. Windridge, V. Mottl, A. Tatarchuk. and A Eliseyev,
The Neutral Point Method for Kernel-Based Combination of Disjoint Training in Multi-Modal Pattern Recognition,
Proceedings of the 7th International Workshop on Multiple Classifier Systems, May, 2007, Springer
[34] D Windridge and J Kittler,
Open-Ended Inference of Relational Representations in the COSPAL Perception-Action Architecture,
Proc. of International Cognitive Vision Workshop (ICVW 2007),
part of 5th International Conference on Computer Vision Systems (ICVS 2007), 2007, Springer
[33] D Windridge, R Patenall and J Kittler,
Factoriality as an Indicator of Stochastic Vector Quantiser Generalising Ability,
CVSSP Technical Report VSSP-TR-5/2007, University of Surrey, UK, 2007
[32] D. Windridge, V. Mottl, A. Tatarchuk. and A Eliseyev,
The Relationship Between Kernel And Classifier Fusion In Kernel-Based Multi-Modal Pattern Recognition:
An Experimental Study,
Proceedings of the International Conference on Machine Learning and Cybernetics 2007 (ICMLC 2007),
August, 2007, Hong Kong, China
[31] J Kittler, M Shevchenko and D Windridge,
Visual Bootstrapping for Unsupervised Symbol Grounding,
Proceedings of 8th Advanced Concepts for Intelligent Vision Systems International Conference, September, 2006,
Springer, eds. J Blanc-Talon and W Philips and D Popescu and P Scheunders, pp 1037-1046
[30] J Kittler, M Shevchenko and D Windridge,
Cognitive Learning with Automatic Goal Acquisition,
Frontiers in Artificial Intelligence and Applications - Third Standing AI Researcher's Symposium, 2006,,
IOS Press, August, eds. L Penserini and P Peppas and A Perini, vol 142, isbn 978-1-58603-645-4.
[29] Bowden R, Ellis L, Kittler J, Shevchenko M, Windridge D.,
Unsupervised Symbol Grounding and Cognitive Bootstrapping in Cognitive Vision,
(Lecture Notes in Computer Science, Vol. 3617, Sept 2005)
[28] D Windridge,
Cognitive Bootstrapping: A Survey of Bootstrap Mechanisms for Emergent Cognition,
CVSSP Technical Report VSSP-TR-2/2005, University of Surrey, UK, 2005.
[27] Josef Kittler, William J. Christmas, Alexey Kostin, F. Yan, Ilias Kolonias, David Windridge,
A Memory Architecture and Contextual Reasoning Framework for Cognitive Vision,
(Lecture Notes in Computer Science, Vol. 3540, June 2005)
[26] David Windridge,
Morphologically Debiased Classifier Fusion: A Tomography-Theoretic Approach,
Advances in Imaging and Electron Physics, vol 134, 2005, Elsevier Academic Press
[25] D. Windridge, R. Bowden,
Hidden Markov chain estimation and parameterisation via ICA-based feature-selection,
Pattern Analysis & Applications, July 2005, vol. 8, pp 115-124,
Publisher: Springer-Verlag London Ltd
[24] David Windridge, Josef Kittler,
Performance Measures of the Tomographic Classifier Fusion Methodology,
Intern. Jrnl. of Pattern Recognition and Artificial Intelligence, Vol. 19
Number 6, 2005
[23] Robin Patenall, David Windridge, Josef Kittler,
Multiple Classifier Fusion Performance in Networked Stochastic Vector Quantisers
Lecture Notes in Computer Science, Vol. 3541, p. 128, June 2005
[22] David Windridge, Robin Patenall, Josef Kittler,
The Relationship Between Classifier Factorisation and Performance
in Stochastic Vector Quantisation
(Lecture Notes in Computer Science, Vol. 3077, June 2004)
[21] D. Windridge, R. Bowden,
Induced Decision Fusion in Automated Sign Language Interpretation:
Using ICA to Isolate the Underlying Components of Sign
(Lecture Notes in Computer Science, Vol. 3077, June 2004)
[20] D. Windridge, R. Bowden, Josef Kittler,
A General Strategy for Hidden Markov Chain Parameterisation in
Composite
Feature-Spaces
(Lecture Notes in Computer Science, Vol. 3138, August 2004)
[19] Richard Bowden, David Windridge, Timor Kadir, Andrew Zisserman, Michael Brady,
A Linguistic Feature Vector for the Visual Interpretation of Sign Language,
European Conference on Computer Vision 2004,
(Lecture Notes in Computer Science, Vol. 3024, pp390)
[18] D. Windridge,
On the Generalisation of Gaussian Mixture Model HMM Parameterisation Techniques,
(Univ. of Surrey Technical Report: VSSP-TR-1/2004), UNIS, UK
[17] D. Windridge, Josef Kittler,
A Morphologically Optimal Strategy for Classifier Combination,
IEEE PAMI, Vol 25, no. 3, March 2003, pp. 343-353
[16] D. Windridge,
Economic Tomographic Classifier Fusion: Eliminating Redundant Hö gbom
Deconvolution Cycles
in the Sum-Rule Domain
(Univ. of Surrey Technical Report: VSSP-TR-1/2003)
[15] D. Windridge, Josef Kittler,
The Practical Performance Characteristics of Tomographically Filtered Multiple Classifier Fusion,
4th International Workshop on Multiple Classifier Systems, 2003,
(LNCS. Vol. 2709, pp. 166 - 175, June 2003)
[14] Josef Kittler, Alireza Ahmadyfard, David Windridge,
Serial Multiple Classifier Systems Exploiting a Coarse to Fine Output
Coding,
4th International Workshop on Multiple Classifier Systems, 2003,
(LNCS. Vol. 2709, pp. 106 - 114, June 2003)
[13] D. Windridge,Josef Kittler,
Morphologically Unbiased Classifier Combination Through Graphical PDF
Correlation,
LNCS 2396, August 2002
[12] D. Windridge,Josef Kittler,
On the General Application of the Tomographic Classifier Fusion Methodology,
LNCS. Vol. 2364, June 2002
[11] Kittler J, Yusoff Y, Christmas W, Windeatt T, Windridge D,
Boosting Multiple Experts by Joint Optimisation of Decision Thresholds,
Pattern Recognition and Image Analysis 11(3), 2001, pp 529-541.
[10] D. Windridge,Josef Kittler,
Classifier Combination as a Tomographic Process,
(Multiple Classifier Systems, LNCS. Vol. 2096 , 2001.)
[9] D. Windridge, S. Phillipps,
A Fluctuation Analysis for Optical Cluster Galaxies - I Theory,
MNRAS (Mon. Not. Roy. Astron. Soc), 319, p. 591, 11/2000
[8] D. Windridge,Josef Kittler,
Combined Classifier Optimisation via Feature Selection,
Advances
in Pattern Recognition, LNCS. Vol. 1876, August 2000.
[7] D. Windridge,
A Generalised Solution to the Problem of Multiple Expert Fusion.
(Univ. of Surrey Technical Report: VSSP-TR-5/2000)
[6] D. Windridge,
A Fluctuation Analysis for Optical Cluster Galaxies, Ph.D. Thesis, University of Bristol, 1999
[5] Groot, P. J.; Galama, T. J.; Vreeswijk, P. M.; Wijers, R. A. M. J.; Pian, E.; Palazzi, E.; van Paradijs,
J.; Kouveliotou, C.; in 't Zand, J. J. M.; Heise, J.; Robinson, C.; Tanvir, N.; Lidman, C.; Tinney, C.;
Keane, M.; Briggs, M.; Hurley, K.; Gonzalez, J.-F.; Hall, P.; Smith, M. G.; Covarrubias, R.; Jonker, P.; Casares, J.;
Frontera, F.; Feroci, M.; Piro, L.; Costa, E.; Smith, R.; Jones, B.; Windridge, D.; Bland-Hawthorn, J.; Veilleux, S.;
Garcia, M.; Brown, W. R.; Stanek, K. Z.; Castro-Tirado, A. J.; Gorosabel, J.; Greiner, J.; Jaeger, K.; Bohm, A. B.;
Fricke, K. J.
The Rapid Decay of the Optical Emission from GRB 980326 and Its Possible Implications,
Astrophysical Journal v.502, August 1998, p.L123 08/1998
[4] Cruikshank, D. P.; Gladman, B.; Smith, R. M.; Jones, J. B.; Windridge, D.; Hall, P.; Graham, D.; Kavelaars, J. J.;
Williams, G. V.; Aksnes, K.; Marsden, B. G.
S/1997 U 1: Precovery and recovery observations of this satellite are reported:
Circular of the Int. Astron. Union., 6870, 1 (1998). 04/1998
[3] Smith, R. M.; Jones, J. B.; Windridge, D.; Gladman, B.; Hall, P.; Graham, D.; Kavelaars, J. J.;
Williams, G. V.; Aksnes, K.; Marsden, B. G.
S/1997 U 2: The recovery of the brighter of the new Uranian satellites is reported
Circular of the Int. Astron. Union., 6869, 1 (1998). 04/1998
[3] Windridge, D.; Phillipps, S.; Birkinshaw, M.
Measures of Galactic and Intergalactic Mass in Clusters.
(P.A.S.P. Proceedings of I.A.U. Symp. No. 179. 1997)
[2] Windridge, D.; Phillipps, S.
The Baryonic and Dark Matter Contribution to Cluster Masses by Dwarf
Galaxies.
(Proceedings of Astronomical Society of the
Pacific, July 1996, p. 329-334.)
[1] Windridge, D, MERLIN observation of the gravitational lens system MG0414+0534,
1996, Research Report,
University of Manchester (Nuffield Radio Astronomy Laboratories)
