ICT
The ways in which machines perceive the world is a constantly evolving field. The Centre for Machine Vision Research (CMV) is at the forefront of creating new ways of improving methods by which computers see both the environment and their users, and it is this area of research that will play one of the most pivotal roles in the emerging fields of augmented reality and natural human-computer interaction
Facial micro-expressions, photograph taken by Jukka Kontinen
it is now one of the key paradigms of face recognition.” The LBP texture operator has been highly
successful in numerous applications around the world, including medical image analysis and aerial image analysis. Tabula Rasa, a project consortium dedicated to addressing some of the issues of direct spoofing attacks to trusted biometric systems, also uses LBP heavily. “For example, some people in the past have been able to fool facial recognition software simply by showing it a picture of a face,” explains Pietikäinen. “Using LBP, the software can now detect this; a real face has a different kind of microstructure and has different lighting variations to a 2D image.” The operator has inspired plenty of new
research on related methods, including the blur-insensitive Local Phase Quantization (LPQ) method, also developed at CMV. It is computationally
very
Advancing methods of machine vision
The Centre for Machine Vision Research (CMV) is a creative, open and internationally renowned research unit in the field of computer vision. It has been open for 32 years, and has a strong record of scientific achievements in both basic and applied research on computer vision. It has achieved ground-breaking research results in many areas
of its activity, including texture
analysis, facial image analysis, geometric computer vision, and energy-efficient architectures for embedded systems. Its central mission is to develop novel computer vision methods and technologies that create a basis for emerging innovative applications. Currently, the main areas of research
are computer vision methods, human- centred vision systems and vision systems engineering.
Computer vision methods The centre has a long and highly successful research tradition in two important generic
82
areas of computer vision: texture analysis and geometric computer vision. In the last few years, the research in computer vision methods has been broadened to cover two new areas: computational photography and object detection and recognition. The aim in all these areas is to create a methodological foundation for development of new vision- based technologies and innovations. Texture is an important characteristic of
many types of images and plays a key role in a wide variety of applications of computer vision and image analysis. The CMV has
long traditions in texture
analysis research and ranks among the world leaders in this area, and is particularly well known for its work with Local Binary Pattern (LBP) methodology. “Around 2004, we proposed how LBP could be used for face recognition and facial image analysis,” recounts Professor Matti Pietikäinen. “Since then, many variants of LBP have been proposed, and
efficient, thus
making it possible to use effectively in real-time for videos. “One of our long term goals is to create a
system by which computers will be able to recognise characteristics of the user; whether they are young or old, male or female, and then be able to react accordingly,” says Pietikäinen. “It will be also be able to recognise
facial expressions and body
movements to analyse emotions. This is an important next step in the field of natural human-computer interaction.”
3D vision for augmented and virtual reality Images are 2D projections of the 3D world, which makes inferring 3D information an ill-posed problem from a single viewpoint, but still a challenging problem from multiple viewpoints. Geometric computer vision provides the tools for establishing a relationship between an image and the 3D scene. While the fundamental theory of geometric computer vision was developed decades ago, problems still exist which require active research. Professor Janne Heikkilä specialises in 3D
vision for augmented and virtual reality. One area that he and his colleagues have focused on has been the development of image-based 3D modelling techniques. These can be used to create 3D virtual models from a set of photographs, which can come from as simple a source as a mobile phone. First of all, a 3D point cloud is created, which
Insight Publishers | Projects
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112