| ¡¡ |
Texture is a
fundamental property of surfaces. It can be seen almost anywhere. For
example, in outdoor scene images, trees, bushes, grass, sky, lakes,
roads, buildings etc. appear as different types of texture. Texture
analysis has been a topic of intensive research for over four decades,
but the progress in understanding how to describe and recognize textures
effectively has been very slow. A wide variety of techniques for
discriminating textures have been proposed. A popular approach is to
divide them into four categories: statistical, geometrical, model-based
and signal processing. Most of the proposed methods have not been,
however, capable to perform well enough for real-world textures and are
computationally too complex to meet the real-time requirements of many
computer vision applications. In recent years, some very discriminative
and computationally efficient local texture descriptors have been
proposed, which has led to a significant progress in applying texture
methods to various computer vision problems. The focus of the research
has moved from 2D textures to 3D textures and spatiotemporal (dynamic)
textures. Due to this progress the application areas of texture
analysis will also be covering such modern fields of computer vision as
face and facial expression recognition, object recognition, background
subtraction, visual speech recognition, and recognition of actions and
gait.
This tutorial
provides an overview to the recent progress of using local texture
descriptors in computer vision. The Local Binary Pattern (LBP) operators
are used as example texture descriptors due to their discriminative
power and computational simplicity.
The presentation is
divided into four parts.
 Part I overviews
the milestones of texture research since the 1960¡¯s, including texture
perception models by Julesz, co-occurrence matrices, Laws texture energy
measures, Gabor filters, random field models, renaissance of texton-based
approaches, and methods based on sparse interest region descriptors.
Part II
deals with the Local Binary Pattern (LBP) operators in the spatial
domain. It also describes how these operators can be used to recognize
3D textured surfaces, implement a SIFT-like interest region descriptor,
recognize faces, and model the background and detect moving objects.
Part III
considers the description of dynamic textures with local spatiotemporal
operators. A simple yet very effective Local Binary Pattern from Three
Orthogonal Planes (LBP-TOP) operator is first described. The use of it
in modeling dynamic events is then considered with applications in
dynamic texture recognition and segmentation, facial expression
recognition, visual speech recognition, recognition of actions and gait,
and video texture synthesis.
Finally,
Part IV concludes the tutorial and outlines challenges for future
research. |
|
 Matti
Pietikäinen
received the Doctor of Science in Technology degree from the University
of Oulu, Finland, in 1982. In
1981, he established the Machine Vision Group at the University of Oulu.
This group has
achieved a highly respected position in its field, and its research
results have been widely exploited in industry. Currently, he is a
professor of information engineering, scientific director of Infotech
Oulu Research Center, and leader of the Machine Vision Group at the
University of Oulu. From 1980 to
1981 and from 1984 to 1985, he visited the Computer Vision Laboratory at
the University of Maryland.
His research interests
include texture-based computer vision, face analysis, activity analysis,
and their applications in human-computer/robot interaction, person
identification, visual surveillance, and image/video retrieval. He has
authored over 200 refereed papers in international journals, books, and
conference proceedings
and about 100 other
publications or reports. His
research on texture-based computer vision, local binary pattern (LBP)
methodology and facial image analysis, for example, is frequently cited
and its results are used in various applications around the world.
He was an associate
editor of the IEEE Transactions on Pattern Analysis and Machine
Intelligence and Pattern Recognition journals. He was guest
editor (with L.F. Pau) of a two-part special issue on ¡°Machine Vision
for Advanced Production¡± for the International Journal of Pattern
Recognition and Artificial Intelligence (also reprinted as a book by
World Scientific in 1996). He was also the editor of the book Texture
Analysis in Machine Vision (World Scientific, 2000) and has served
as a reviewer for numerous journals and conferences.
He was the president of the Pattern
Recognition Society of Finland from 1989 to 1992.
From 1989 to 2007 he served
as a member of the Governing Board of the International Association for
Pattern Recognition (IAPR), and became one of the founding fellows of
the IAPR in 1994. He regurarly
serves on program committees of the top conferences and workshops of his
field. Recently, he
was an area chair of
IEEE Conference on Computer
Vision and Pattern Recognition (CVPR ¡®07), a co-chair of Workshops of
International Conference on Pattern Recognition (ICPR ¡®08), a co-chair
of ECCV 2008 Workshop on Machine Learning for Vision-based Motion
Analysis (MLVMA), and is a co-chair of MLVMA workshop at ICCV 2009.
He is a senior
member of the IEEE, and was the vice-chair of IEEE Finland Section.
¡¡ |
|
 Guoying
Zhao
received the Ph. D. degree in computer science from the Institute of
Computing Technology, Chinese Academy of Sciences, Beijing, China in
2005. Since July 2005, she has been a Postdoctoral Research Fellow in
Machine Vision Group at the University of Oulu.
Her research interests include gait
analysis, dynamic texture recognition, facial expression recognition,
human motion analysis, and person identification.
She has authored over 50
papers in journals and conferences, and has served as a reviewer for
many journals and conferences. She
gave an invited talk ¡°Dynamic Texture Recognition Using Local Binary
Patterns with an Application to Facial Expressions¡± in Institute of
Computing Technology, Chinese Academy of Sciences, July 2007. With Prof.
Pietikäinen, she gave a tutorial: ¡°Local
Binary Pattern Approach to Computer Vision¡± in 18th ICPR,
Aug. 2006, Hong Kong.
She is authoring/editing
three books: springer book Computer Vision Using Local Binary
Patterns; springer book Machine Learning for Vision-based Motion
Analysis; IGI global book Machine Learning for Human Motion
Analysis: Theory and Practice. She is guest editor of the special
issue New Advances in Video-based Gait
Analysis and Applications: Challenges and Solutions
on
IEEE Transactions on Systems, Man, and
Cybernetics¡ªPart B: Cybernetics.
She was a co-chair
of ECCV 2008 Workshop on Machine Learning for Vision-based Motion
Analysis (MLVMA), and is a co-chair of MLVMA workshop
at ICCV 2009.
¡¡ |
