Biographies for all those members within the Machine Vision Centre
Professor Melvyn L. Smith BEng, MSc, PhD, CEng, MIEE
Professor of Machine Vision
Melvyn L. Smith is Professor of Machine Vision and Director of the Centre for Machine Vision (CMV) at UWE Bristol. He received his BEng (Hons) degree in Mechanical Engineering from the University of Bath in 1987, MSc in Robotics and Advanced Manufacturing Systems from the Cranfield Institute of Technology in 1988 and PhD from UWE in 1997.
He acts as associate editor for four leading international journals, including Computers in Industry, for which he is currently guest editing a special issue on 3D imaging. He has published a book on computer vision for surface inspection together with numerous book chapters, patents and journal/conference papers in connection with his work. He has been a member of the EPSRC Peer Review College since 2003 and is currently a programme and evaluator/review/monitoring expert for the EU Framework 7 Programme. Professor Smith is a Chartered Engineer and an active member of the IET.
Professor Lyndon N. Smith BSc(Hons), MSc, PhD
Professor in Computer Simulation and Machine Vision
Lyndon Smith is Professor in Computer Simulation and Machine Vision, in the Centre for Machine Vision at UWE Bristol. Following a BSc (Hons) in Physics in 1986, he went on to obtain an MSc in Automation in 1988 and a PhD in computer simulation of a manufacturing process in 1997. He has over 20 years of experience of research (on both sides of the Atlantic), in the field of Computer Simulation and Machine Vision, with particular emphasis on 3D analysis of complex surface textures and object morphologies. He developed a high-resolution 3D texture vision system (the Skin Analyser), which has been employed over a number of years at Frenchay Hospital, for analysis of potentially cancerous skin lesions.
His computer simulations, which have included Monte Carlo techniques and neural networks, resulted in a new method for 3D object analysis that has been employed by other researchers as well as being developed into commercial software. Research outcomes have included 17 successful PhD supervisions, 150 papers - 90 in international journals (the full manuscripts of many of these are available through ResearchGate), two books, being named as inventor in five patent applications, and working prototype and commercial systems that have been delivered to clients internationally.
Dr. Abdul R. Farooq BSc(Hons), MSc(Dist), PhD, FHEA, CEng MIET
Dr. Abdul R. Farooq BSc(Hons), MSc(Dist), PhD, FHEA, CEng MIET
Associate Head of Department – Electronics and Robotics
Dr Abdul Farooq is Associate Head of Department and a senior member of the Centre for Machine Vision, Bristol Robotics Laboratory. He is an active researcher and his research is focused on developing new vision based techniques for the inspection of complex surfaces in real time and in the research, design and manufacture of medical imaging devices. Abdul lectures in Machine Vision, Design and CAD/CAM. He graduated from Cardiff University in 1990 with a first degree in Electronics and subsequently successfully completed an MSc in Systems Engineering (Robotics and Automation) in 1992. He then worked for a number of years as a Systems Engineer at a leading edge high-volume board manufacturing plant. Following this, Abdul was drawn back to academia and completed (with distinction) a further Masters degree, followed by a PhD in Machine Vision.
Abdul has been and involved with a number of successful projects and bids within the group, and lead an exceptional Knowledge Transfer Partnership which was awarded a grade A and considered 'Outstanding' by Innovate UK. His research outcomes have included successful PhD supervisions and a number of journal papers. Abdul is a Fellow of the Higher Education Authority, member of the IET and a Chartered Engineer.
Dr. Gary A. Atkinson MSci, PhD, MInstP
Gary Atkinson completed an MSci degree in physics at the University of Nottingham in 2003. Upon graduation, he moved to the University of York to study for a PhD degree in the Department of Computer Science, under the supervision of Edwin Hancock. His research was concerned with improving shape recovery algorithms and reflectance function estimation for computer vision. Most of his work involved the exploitation of the polarising properties of reflection from surfaces.
Since 2007, Gary has worked for UWE Bristol/BRL and carried out research in a range of areas including 3D face recognition, medical imaging, agri-tech, industrial inspection, and physics-based vision. In 2010, he acted as the editor and UK and Europe co-convener for the International Conference and Exhibition on Biometrics Technology in Coimbatore, India. Gary runs teaching modules in MATLAB programming, mechanics, computer vision and inspection.
Senior Lecturer in Engineering
Khem Emrith is currently a Senior Lecturer in Engineering in the Centre for Machine Vision, Bristol Robotics Lab. Prior to being appointed a Lecturer, Dr. Emrith worked as a Post-Doctoral Research Associate (2010-2014) at the Centre for Machine Vision and also a Post-Doctoral Research Associate (2008-2010) at the Texture Lab, Heriot-Watt University. Dr. Emrith's research interest covers primarily capture, recovery and characterisation of 3D surface geometry and 3D surface Texture and spans areas such as Dynamic Facial Movement and Expression modelling and 3D Surface Texture Perception and Retrieval. Other areas of interests include the 3D modelling of the micro-geometry of paper substrates and the 3D characterisation of mucosal tissue. Dr. Emrith completed a PhD from Texture Lab, Heriot Watt University,in 2008 on Perceptual Dimensions for 3D Surface Texture Retrieval. He did a Masters by Research from the MOIVRE Lab, Sherbrooke University (1999-2001) on Content Based Image Retrieval using Relevance Feedback.
Dr. Mark F. Hansen BSc(Hons), MSc, PhD
Mark obtained his BSc Psychology (1997) and MSc Computer Science (1999) from the University of Bristol and worked as a software developer for just under a decade. Using a photometric stereo technique developed as part of the PhotoFace project at UWE, he gained his PhD in 2012 by bridging the gap between psychology and machine vision to develop novel face recognition algorithms inspired by human processes such as caricaturing.
Highlights of his research include demonstrating that the overall geometry of reconstruction of faces can be improved by replacing the flashguns on the Photoface device with near infrared LEDs and showing that large amounts of common data in faces can be discarded with only a small impact on recognition accuracy. Accuracies of over 95% at a False Acceptance Rate of 1 in 1,000 were achieved using only 10x10 pixel surface normal representations.
He has applied his expertise across diverse areas from security to agri-tech sectors; from 3D handprint recognition to dairy herd welfare monitoring. He is currently a Research Fellow working on pig-face recognition and using photometric stereo to enhance phenotype measurement in plants.
Varun Kakra BEng, MSc
Varun obtained his Bachelor's degree (BEng) in Electronics and Telecommunications from VIIT, University of Pune, India in 2008. He then worked as Research Assistant on Computer Vision and Image Processing projects in the R&D department at VIIT after his graduation. He then obtained his Master's degree (MSc) in Vision, Image and Signal Processing from Heriot-Watt University in Edinburgh in 2010. His Master's thesis was titled 'Normative Brain Atlas Viewer' which was conducted at Toshiba Medical Visualisation Systems Europe, Edinburgh under the supervision of Dr Ian Poole and Dr Yvan Petillot.
After this, he worked as a Research Fellow at Noldus Information Technology (NIT) under the supervision of Dr Nico van der Aa for three years, where was involved in the iCareNet project as a Marie Curie researcher. His research focused on activity recognition by computer vision and machine learning techniques relating to human eating behaviour.
He has also worked as a freelancer where he worked on projects involving 3D stereo reconstruction using structure-from-motion approach and real-time image recognition.
Dr. Tim Volonakis BSc, PhD
Tim obtained his BSc in Computing (2012) at Anglia Ruskin University. It was here where he first became fascinated with vision, being supervised by Dr Ian van der Linde. Tim then completed his Psychology PhD at the University of Bristol, in the school of Experimental Psychology (2016), supervised by Roland Baddeley, Nicholas Scott-Samuel, and Innes Cuthill. Tim was a part of the camouflage lab at Bristol, a subset of the Bristol Vision Institute.
Tim’s PhD was directly concerned at replacing human observers with an artificial automated visual system at evaluating military camouflage concealment. Camouflage is a difficult problem for machines, because object recognition is already non-trivial, and camouflaged objects are purposely less visible. The artificial visual system to replace humans at this task ought to be designed in accordance with principles of the human visual system. It is for this reason he did his PhD in Psychology where he gained appreciation of the human visual system and human experimental design. Tim’s PhD also looked at face recognition, and texture perception. Tim’s undergraduate dissertation was also concerned with camouflage; it attempted to simulate natural evolution evolving camouflage patterns, using a classical visual search human experiment.
Tim started a research associate position in the centre for machine vision at the UWE Bristol in December 2016. He is primarily working on a project towards automated windscreen crack assessment for Belron, known in the UK as Autoglass. This involves identification and segmentation of a windscreen crack in real-world conditions. Tim is also working on a weed-detection project lead, by Varun Kakra that is funded by Soil Essentials. Soil Essentials would like a real-time system that can detect weeds for spraying as it moves across a field.
Wenhao Zhang BEng, MEng, MSc
Wenhao Zhang obtained his BEng Automation (2010) and MEng (MRes) Control Theory and Control Engineering (2013) from Wuhan University of Science and Technology (WUST) in China. He also holds an MSc with distinction from the University of the West of England (UWE) in Advanced Technologies in Electronics (2013). This MSc project, in collaboration with a security company, involved development of an intelligent vision-based camera detection algorithm along with a smart anti-piracy system to uncover illegally smuggled camcorders in cinemas and theatres. Under the supervision of Professor Melvyn Smith, Wenhao based his PhD research on a project from the Centre for Machine Vision (CMV), Bristol Robotics Lab (BRL). This research explores facial cues, such as gender, age and gaze, by performing 2D and 3D-based computer vision analysis. The ultimate aim is to create a natural Human-Computer Interaction strategy that can fulfil user expectations, augment user satisfaction and enrich user experience by understanding user characteristics and behaviours. Wenhao is currently a Research Associate at the CMV, and he has worked on 3D face imaging for rail systems and 4D hyperspectral imaging for agriculture.
Michael Miller BSc (Hons), AMIMA
Mike Miller obtained his BSc Mathematics from UWE in 2014, receiving an ‘Institute of Mathematics and its Applications’ (IMA) prize for outstanding achievement as best student in mathematics and statistics, with a dissertation based on the conformal mapping of two-dimensional potential fluid flow. In October 2014, he was offered a studentship from UWE and the company Grade 2 Ltd to join the CMV as a doctoral researcher, working on the project ‘Defect detection in complex natural and pseudo-natural concomitant two-dimensional textures’. The aim of the project, in collaboration with Grade 2 Ltd, is to develop software that is able to differentiate subtle ‘defective’ regions in complex textures - for example identifying a tumour in an MRI scan, or an ink blob on a manufactured tile. Current methods have struggled when attempting to pick out these types of region amongst complex underlying textures, so Mike has been working on a combination of approaches, such as wavelet and Fourier analysis, statistical machine learning and other classical machine vision techniques to approach this project. Further work may include looking into three-dimensional defective regions.
Gytis Bernotas BEng (Hons)
Gytis Bernotas obtained his BEng Robotics from UWE Bristol in 2015. During his last year of the degree he developed an interest in machine vision and it played a crucial role in his dissertation titled 'Tele-operation and blended-control'. Soon after the graduation Gytis was offered a studentship from UWE Bristol and CMV to join the CMV as a doctoral researcher, exploring machine vision applications for plant phenotyping. In recent years advances in imaging techniques have primarily focused on two-dimensional imaging approaches. However, the accuracy of 2D measurements is limited by the viewpoint of the camera relative to the plant surface. Three-dimensional imaging techniques can overcome such shortcomings, but are often limited in speed, image resolution and affordability, which illustrates the need for new 3D data acquisition methodologies, so Gytis has been working on developing a plant phenotyping system that utilises the Photometric Stereo technique to achieve a low-cost, yet, high-resolution, fast and accurate solution to this problem. Future work may incorporate spectral imaging of plants to accomplish a multi-modal system.
Lili Tao is a Senior Lecturer in Machine Vision in the Centre of Machine Vision, Bristol Robotics Laboratory. She is also an Honorary Researcher at the University of Bristol. Before joining UWE Bristol, she was a Postdoctoral Research Associate at the University of Bristol (from 2013 to 2017). While there, she worked on the SPHERE project, applying computer vision techniques to help diagnosing and managing health and well-being conditions in home-based environments. Before that, she received a BEng degree with a first class honours in Digital Signal and Image Processing (2010), and a PhD degree (2013), both from the University of Central Lancashire, UK. Her PhD research was focused on recovering the 3D non-rigid object and camera motion from a monocular video sequence.
Her research area is computer vision. She is particularly interested in developing methods for estimating and analysing deformable and articulated objects, such as human motion modelling and analysis, physical activity monitoring and facial articulated assessment.
Dr. P. Sagar Midha BSc Eng(Mech), PhD, CEng, MIEE
Sagar Midha is currently working in a part-time role as senior research fellow. Prior to this, he was a reader and research leader in the Faculty Computing Engineering and Mathematical Sciences (now part of the Faculty of Environment and Technology) and a Principal Engineer at PERA International at Melton Mowbray in Leicestershire. He received his BSc Engineering degree in Mechanical Engineering from Punjab University in India and his PhD from Loughborough University in 1975.
He has edited two books and published numerous journal and conference papers. Sagar developed several successful research proposals for funding and was a coordinator for two EU-funded research projects. His pioneering work for collaborative links for postgraduate courses with India led to the development of Faculty's present international collaborative programmes.
Ian Hales BSc PhD
Ian Hales obtained his BSc Computer Science from the University of Leeds in 2009, staying on there to undertake a PhD under the supervision of David Hogg and Kia Ng. His research involved the reconstruction of accurate ground-planes in pedestrian scenes of varying complexity using only the motion of tracked features above the plane. At CMV Ian has worked on automated weed detection in maize crops at high frame rates, using tried-and-tested computer vision methods to achieve high levels of accuracy. As part of this work, he developed and integrated a variety of software and hardware solutions to provide a flexible platform for data capture and analysis.
The agri-tech sector is one in which Ian has a keen interest and he is currently developing material for early-stage bids regarding automated weed control and in-situ plant phenotyping. Ian is currently working on a project for long-range 3D surface reconstruction, which uses novel sensor technologies in combination with state-of-the-art photometric stereo techniques to allow imaging in difficult conditions, such as bright sunlight and over long distances – potentially up to hundreds of metres. Ian has also contributed towards grant applications to a range of funding bodies, including EPSRC, BBSRC and InnovateUK; and is keen to build further collaborative relationships with both academic and industrial institutions.