The Computer Vision and Machine Learning (CVML) Research Group emerged as a result of a cross-disciplinary interests in research and applications related to Computer Vision, Machine Learning and Medical Image Computing. The main focus of the group is to research, develop and deploy novel methods for analysis of visual information for medical and industrial applications. The group have led or been involved in a number of industry, EPSRC, FP7 and HEIF funded projects. The ongoing emphasis is on developing new vision and machine learning algorithms and their transfer to real world applications. The particular areas of interest include: Bayesian methodology for data modelling, pattern recognition and tracking; statistical shape analysis; deformation modelling for model-based recognition, segmentation and registration; medical imaging; intelligent energy management; data mining; and applications of deep learning.
The ongoing progress in the mathematical tools, the growing prevalence of very large datasets, ever-increasing computational power and progress in imaging devices established the computer vision and machine learning as mature scientific disciplines with rapidly growing number of exploitations in wide spectrum of applications, such as machine condition monitoring, medical diagnosis, assistive living or autonomous vehicles to name just a few. The CVML group have a wide ranging skills, combing expertise from different disciplines, including: engineering, physics, computing and media. The group activities are supported by a dedicated research laboratory with various vision systems including number of static and dynamic 3D scanning devices, multi-camera acquisition and lighting systems, as well as dedicated GPU computing facilities. The activities of the group are further supported by the international collaborations, including Information Processing and System Teams (ETIS) at Cergy-Pontoise University, I3S laboratory at the University of Cote d’Azur, or Signals and Images Laboratory at the Institute of the National Research Council of Italy (CNR) in Pisa, Computer Support for Medical Diagnosis & Therapy Procedures & Operations Group at the AGH University of Science and Technology in Kraków.
A sample of CVML applications, from left to right: (i) level-set object segmentation with statistical shape prior; (ii) head-pose estimation from depth camera; (iii) eye status detection from video
Henriquez Castellano, Pedro, Matuszewski, Bogdan J., Andreu-Cabedo, Yasmina, Bastiani, Luca, Colantonio, Sara, Coppini, Giuseppe, D'Acunto, Mario, Favilla, Riccardo, Germanese, Danila et al (2017) Mirror mirror on the wall... an unobtrusive intelligent multisensory mirror for well-being status self-assessment and visualization. IEEE Transactions on Multimedia, 19 (7). pp. 1467-1481.
Bernal, Jorge, Tajbakhsh, Nima, Sanchez, F. Javier, Matuszewski, Bogdan J., Chen, Hao, Yu, Lequan, Angermann, Quentin, Romain, Olivier, Rustad, Bjorn et al (2017) Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results from the MICCAI 2015 Endoscopic Vision Challenge. IEEE Transactions on Medical Imaging, 36 (6). pp. 1231-1249.
Yasmina Andreu, Franco Chiarugi, Sara Colantonio, Giorgos Giannakakis, Daniela Giorgi, Pedro Henriquez Castellano, Eleni Kazantzaki, Dimitris Manousos, Kostas Marias, Bogdan Matuszewski, Maria Antonietta Pascali, Matthew Pediaditis, Giovanni Raccichini, Manolis Tsiknakis, Wize Mirror - a smart, multisensory cardio-metabolic risk monitoring system. Computer Vision and Image Understanding, Vol. 148, pp. 3-22, July 2016.
Tao, Lili and Matuszewski, Bogdan J., (2016) Robust Deformable Shape Reconstruction from Monocular Video with Manifold Forest. Machine Vision and Applications, 27 (6). pp. 801-819.
Veta, Mitko, van Diest, Paul J., Willems, Stefan M., Wang, Haibo, Madabhushi, Anant, Cruz-Roa, Angel, Gonzalez, Fabio, Larsen, Anders B.L., Vestergaard, Jacob S. et al (2014) Assessment of algorithms for mitosis detection in breast cancer histopathology images. Medical Image Analysis, 20 (1). pp. 237-248.
Quan, Wei, Matuszewski, Bogdan J., and Shark, Lik (2015) Statistical shape modelling for expression-invariant face analysis and recognition. Pattern Analysis & Applications . pp. 1-17.
Quan, Wei, Matuszewski, Bogdan J., and Shark, Lik (2016) 3-D Face Recognition Using Geodesic-Map Representation and Statistical Shape Modelling. Lecture Notes in Computer Science, 9493 . pp. 199-212.
Song, Zhuoyi, Zhou, Yu and Juusola, Mikko (2017) Modeling elucidates how refractory period can provide profound nonlinear gain control to graded potential neurons. Physiological reports, 5
Song, ZH, Zhou, Yand Juusola, M (2016) Random Photon Absorption Model Elucidates How Early Gain Control in Fly Photoreceptors Arises from Quantal Sampling. Frontiers in Computational Neuroscience, 10 .
Pretorius, AJ, Zhou, Yu and Ruddle, R (2015) Visual parameter optimisation for biomedical image processing. BMC Bioinformatics, 16 (S9). pp. 1-13.
Furfaro, Roberto, Wibben, Daniel, R., Gaudet, Brian and Simo, Jules (2015) Terminal multiple surface sliding guidance for planetary landing: Development, tuning and optimization via reinforcement learning. Journal of the Astronautical Sciences, Vol. 62(1), pp.73-99.
Simo, Jules, Furfaro, Roberto, and Mueting, Joel (2015) Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. In: Advances in the Astronautical Sciences. Advances in the Astronautical Sciences, 155. Univelt Inc, USA, pp. 2233-2248.