Publications
157 results found
Dosis A, Bello F, Aggarwal R, et al., 2005, Synchronised video and motion analysis for the assessment of procedures in the operating theatre, Archives of Surgery, Vol: 140, Pages: 293-299
Lam YF, Boswell DD, Gillies DF, et al., 2005, A shape model of the human mandible, Meeting of the Anaesthetic-Research-Society
- Author Web Link
- Cite
- Citations: 1
Marvasti S, Gillies D, Markus HS, 2005, Novel intelligent wavelet filtering of embolic signals from TCD ultrasound, Westerville, conference on models - third dimension of science, 16 September 2003, Munich, GERMANY, Publisher: Amer Ceramic Soc, Pages: 1580-1584
Dosis A, Bello F, Gillies D, et al., 2005, Laparoscopic Task Recognition Using Hidden Markov Models, MEDICINE MEETS VIRTUAL REALITY 13: THE MAGICAL NEXT BECOMES THE MEDICAL NOW, Vol: 111, Pages: 115-122, ISSN: 0926-9630
- Author Web Link
- Cite
- Citations: 16
Thomaz CE, Gillies DF, Feitosa RQ, 2004, A new covariance estimate for Bayesian classifiers in biometric recognition, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, Vol: 14, Pages: 214-223, ISSN: 1051-8215
- Author Web Link
- Cite
- Citations: 62
Marvasti S, Gillies D, Markus HS, 2004, Novel intelligent wavelet filtering of embolic signals from TCD ultrasound, Departmental Technical Report: 04/7, Publisher: Department of Computing, Imperial College London, 04/7
Transcranial Doppler ultrasound can be used to detect emboli in blood flow for predictingstroke. Embolic signals have characteristic transient chirps suitable for wavelet analysis.We have implemented and evaluated the first on-line intelligent wavelet filter to amplifyembolic signals building on our previous work in detection. Our intelligent waveletamplifier uses the matching filter properties of the Daubechies 8th order wavelet toamplify embolic signals. Even the smallest embolic signal is enhanced without affectingthe background blood flow signal. We show an increase of over 2db (on average) inembolic signal strength and an improvement in detection of 10-20%.
Thomaz CE, Gillies D, 2004, A maximum uncertainty LDA-based approach for limited sample size problems – with application to Face Recognition, Departmental Technical Report: 04/1, Publisher: Department of Computing, Imperial College London, 04/1
A critical issue of applying Linear Discriminant Analysis (LDA) is both thesingularity and instability of the within-class scatter matrix. In practice, particularly inimage recognition applications such as face recognition, there are often a large number ofpixels or pre-processed features available, but the total number of training patterns islimited and commonly less than the dimension of the feature space. In this paper, a newLDA-based method is proposed. It is based on a straighforward stabilisation approach forthe within-class scatter matrix. In order to evaluate its effectiveness, experiments on facerecognition using the well-known ORL and FERET face databases were carried out andcompared with other LDA-based methods. The results indicate that our method improvesthe LDA classification performance when the within-class scatter matrix is notonly singular but also poorly estimated, with or without a Principal Component Analysisintermediate step and using less linear discriminant features.
Thomaz CE, Boardman JP, Hill DLG, et al., 2004, Using a maximum uncertainty LDA-based approach to classify and analyse MR brain images, Berlin, 7th international conference on medical image computing and computer - assisted intervention (MICCAI 2004), St Malo, France, Publisher: Springer-Verlag, Pages: 291-300
Dosis A, Bello F, Moorthy K, et al., 2004, Real-time synchronization of kinematic and video data for the comprehensive assessment of surgical skills, Amsterdam, 12th conference on medicine meets virtural relity, Newport Beach, CA, 2004, Publisher: I O S Press, Pages: 82-88
Dosis A, Bello F, Moorthy K, et al., 2004, Real-time synchronization of kinematic and video data for the comprehensive assessment of surgical skills, MEDICINE MEETS VIRTUAL REALITY 12, Vol: 98, Pages: 82-88, ISSN: 0926-9630
- Author Web Link
- Cite
- Citations: 13
Marvasti SA, Gillies D, Marvasti F, et al., 2004, On-line automated detection of cerebral embolic signals using a wavelet based system, Ultrasound in Medicine and Biology, Vol: 30, Pages: 647-653
Thomaz CE, Boardman JP, Hill DLG, et al., 2004, Whole brain voxel-based analysis using registration and multivariate statistics, Proceedings of medical image understanding and analysis '04, 2004, Pages: 73-77
Lam YF, Gillies DF, Rueckert D, et al., 2003, Obtaining corresponding landmarks of the human mandible, Meeting of the Anaesthetic-Research-Society
- Author Web Link
- Cite
- Citations: 1
Bang J-W, Pappas A, Gillies D, 2003, Interpretation of hidden node methodology with network accuracy, Departmental Technical Report: 03/2, Publisher: Department of Computing, Imperial College London, 03/2
Bayesian networks are constructed under a con-ditional independency assumption. This assump-tion however does not necessarily hold in prac-tice and may lead to loss of accuracy. We previ-ously proposed a hidden node methodology whereby Bayesian networks are adapted by the addition of hidden nodes to model the data de-pendencies more accurately. Empirical results in a computer vision application to classify and count the neural cell automatically showed that a modified network with two hidden nodes achieved significantly better performance with an average prediction accuracy of 83.9% com-pared to 59.31% achieved by the original net-work. In this paper we justify the improvement of performance by examining the changes in network accuracy using four network accuracy measurements; the Euclidean accuracy, the Co-sine accuracy, the Jensen-Shannon accuracy and the MDL score. Our results consistently show that the network accuracy improves by introduc-ing hidden nodes. Consequently, we were able to verify that the hidden node methodology helps to improve network accuracy and contribute to the improvement of prediction accuracy.
Thomaz CE, Gillies DF, 2003, A new fisher-based method applied to face recognition, Berlin, 10th international conference on computer analysis of images and patterns, Groningen, Netherlands, 2003, Publisher: Springer-Verlag, Pages: 596-605
Thomaz CE, Gillies DF, 2003, Visual analysis of the use of mixture covariance matrices in face recognition, Berlin, 4th international conference on audio- and video-based biometric person authentication, University of Surrey, Guildford, England, 2003, Publisher: Springer-Verlag, Pages: 172-181
Thomaz C, Feitosa R, Gillies D, 2003, Using Mixture Covariance Matrices to Improve Face and Facial Expression Recognitions, Publisher: Elsevier, Pages: 2159-2165, ISSN: 0167-8655
In several pattern recognition problems, particularly in image recognition ones, there are often a large number of features available, but the number of training samples for each pattern is significantly less than the dimension of the feature space. This statement implies that the sample group covariance matrices often used in the Gaussian maximum probability classifier are singular. A common solution to this problem is to assume that all groups have equal covariance matrices and to use as their estimates the pooled covariance matrix calculated from the whole training set. This paper uses an alternative estimate for the sample group covariance matrices, here called the mixture covariance, given by an appropriate linear combination of the sample group and pooled covariance matrices. Experiments were carried out to evaluate the performance associated with this estimate in two recognition applications: face and facial expression. The average recognition rates obtained by using the mixture covariance matrices were higher than the usual estimates.
Bang JW, Pappas A, Gillies D, et al., 2003, Interpretation of hidden node methodology in automated classification of neural cell morphology, Athens, International conference on mathematics and engineering techniques in medicine and biological science, Las Vegas, Nevada, 2003, Publisher: C S R e A Press, Pages: 527-532
Lam YF, Gillies DF, Rueckert D, et al., 2003, Generic anatomical model of the human mandible, IASTED Biomech 2003, Publisher: ACTA Press, Pages: 247-251
Gillies DF, Bourmpos M, 2003, Modelling soft tissue deformation using principal component analysis and haptic devices, IASTED Biomech 2003, Publisher: ACTA Press, Pages: 287-302
Groom P, Johnstone J, Charters P, et al., 2002, The effect of airway manoeuvres and route of respiration on spatial orientation of the upper airway, BRITISH JOURNAL OF ANAESTHESIA, Vol: 89, Pages: 205P-205P, ISSN: 0007-0912
Lam YF, Gillies DF, Charters P, et al., 2002, Determining natural variation through eigenvector projections in the human airway, BRITISH JOURNAL OF ANAESTHESIA, Vol: 89, Pages: 204P-204P, ISSN: 0007-0912
Gomez G, Sucar LE, Gillies DF, 2002, Navigation advice from pq-histograms, Berlin, 2nd Mexican international conference on artificial intelligence, Merida, Mexico, 2002, Publisher: Springer, Pages: 31-40
Bang JW, Gillies D, 2002, Using bayesian networks to model the prognosis of hepatitis C, 7th workshop on intelligent data analysis in medicine and pharmacology (IDAMAP.02), Lyon, France, 2002, Publisher: N/A, Pages: 7-15
Heesch D, Hoare J, Gardoni M, et al., 2002, Content based sketch retreival and relevance feedback, SSGRR2002, advances in Infrastructure for e-business, e-education e-science and e-medicine on the internet
Pappas A, Gillies DF, 2002, A new measure for the accuracy of a bayesian network, Berlin, 2nd Mexican international conference on artificial intelligence, Merida, Mexico, 2002, Publisher: Springer, Pages: 411-419
Lam YF, Gillies DF, 2002, Capturing the shape variation of the upper human airway, MIUA conference, Portsmouth University, July 2002, Publisher: ACTA Press, Pages: 36-40
Thomaz CE, Gillies DF, Feitosa RQ, 2002, A new quadratic classifier applied to biometric recognition, New York, Canadian Society for Computational Studies of Intelligence; advances in artificial intelligence, Publisher: Springer, Pages: 186-196, ISSN: 0302-9743
Bang JW, Gillies D, 2002, Using bayesian networks with hidden nodes to recognise neural cell morphology, New York, 7th Pacific Rim international conference on artificial intelligence, PRICAI 20002 trends in artificial intelligence, Tokyo, Publisher: Springer, Pages: 385-394
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.