Visual Recognition Tutorial
Jiri Matas, CTU Prague, Czech Republic
Krystian Mikolajczyk, U. of Surrey, UK
General, robust, real-time, learnable visual recognition and
categorisation for large number of classes is one of the ultimate
goals of computer vision. The current state of the art includes
methods that fulfill some of the requirements in some restricted domains.
For example, methods for real-time recognition of a very large number
of locally flat, highly textured, rigid specific objects exist (e.g.
Nister & Stewenius CVPR 06); in categorisation the state of the art
algorithms can handle objects from tens of (carefully chosen)
categories (e.g. Opelt CVPR 06). For some classes, e.g. faces, a
robust and fast solution exist in fairly general settings (Viola
Jones, ICCV 01). The above-mentioned approaches all have different
structure, and as yet no unifying paradigm has emerged.
In the tutorial, we will first present the state of the art on
selected case studies. The methods will be dissected and their
assumption and components identified. In the second part, the
key components and algorithms and their will be analysed and
compared in depth:
- learning methods, level of supervision
- matching and search methods, search in pose space v. correspondence
- object representation: appearance, features-based, edges, holistic
- robustness to occlusion, clutter,
- indexing methods
In the third part, we will put the current progress into perspective
by reviewing "forgotten" problems and listing open problems, such as
recognition of objects without surface texture (including the world of
polyhedra), of wire-like object where any local patch includes
background, of semi-transparent objects etc.
Biographies of organisers
received the MSc degree in cybernetics (with honours) from
the Czech Technical University, Prague, Czech Republic, in 1987 and the
PhD degree from the University of Surrey, UK, in 1995. From 1991 to
1997 he was a research fellow at the University of Surrey. In 1997, he
joined the Center for Machine Perception at the Czech Technical
University in Prague. He has published more than hundred papers in
refereed journals and conferences. His work has more than eight hundred
citations in the Science Citation Index. He received the best paper
prize at the British Machine Vision Conferences in 2002 and 2005. J.
Matas has served in various roles at international conferences (e.g.
ICCV, CVPR, ICPR, NIPS), co-chairing ECCV 2004 and CVPR 2007. His
research interest include object recognition, sequential pattern
recognition, invariant feature detection, and Hough Transform and
received the MS degree in electrical engineering
from the University of Science and Technology, Cracow, Poland in 1997
and the PhD degree (2002) in computer vision from the Institut National
Polytechnique de Grenoble (INPG), France. Dr. Mikolajczyk was a
postdoctoral research assistant in the Robotics Research Group of
Oxford University in 2002- 2004. He is currently a research assistant
at the Technical University of Darmstadt, Germany, and a lecturer at
the University of Surrey, United Kingdom. His research interests
include invariant feature detection, object and scene recognition, as
well as machine learning methods in vision.