Download Image Processing

Image
Processing
Image
Processing
•
•
Class 1
Introduction
Image
Processing
•
1
•
– Oral or written exam (depends on the number of participants)
after the lecturing period
– Regular attendance in the tutorials required to qualify for the exam
•
These slides will be made available at
http://www.inf.tu-dresden.de/content/institutes/ki/is/bv_ws0708.de.html
•
They are password protected. Access via…
© 2007 Thomas Brox
Image
Processing
Grading policy
Tutorials start next week
Prerequisites
– Undergraduate mathematics
– Some programming experience in C/C++
(for the programming assignments)
Organizational issues
•
What type of lecture?
– 2 hours classroom lecture, 2 hours tutorials
– Tutorial consisting of mostly programming assignments and some theoretical
assignments
– Introductory course in the fields of image processing, computer vision, and
pattern recognition
– (Soft) requirement for starting a diploma thesis in this field
Image Processing
© 2007 Thomas Brox
Organizational issues
2
Other courses
This winter term:
– Pattern Matching in Computer Vision (2+2, called Mustererkennung)
•
Next summer term (planned):
– Computer Vision (2+2)
– Image Segmentation (2+2)
or Pattern Recognition and Machine Learning (2+2)
– username: open
– password: sesame
© 2007 Thomas Brox
3
© 2007 Thomas Brox
4
Image
Processing
Image
Processing
What is an image?
Where do images and image processing play a role?
•
Imaging (e.g. photography, ultrasound, x-ray, magnetic resonance)
•
Image enhancement (e.g. Adobe Photoshop)
•
Image and video compression
•
Computer graphics (model Æ image)
•
Computer vision (image Æ model)
•
Focus of this and the following courses: image enhancement and
computer vision
Author: Daniel Cremers
•
Digital image: regular grid
•
Continuous function
of intensity values
© 2007 Thomas Brox
Image
Processing
5
Image
Processing
Imaging – ultrasound, MRI
Ultrasound image of a human embryo
© 2007 Thomas Brox
© 2007 Thomas Brox
6
Image enhancement - denoising
Magnetic resonance image of a
human head
7
© 2007 Thomas Brox
8
Image
Processing
Image
Processing
Image enhancement - deblurring
Image compression - JPEG
Welk et al. 2005: variational deblurring
© 2007 Thomas Brox
Image
Processing
9
© 2007 Thomas Brox
Image
Processing
Computer graphics – water simulation
10
Computer vision – 3D reconstruction
Kolev et al. 2007: multiview reconstruction
Guendelman et al. 2005: Simulating the flow of water with level sets
© 2007 Thomas Brox
11
© 2007 Thomas Brox
12
Image
Processing
Image
Processing
Computer vision - segmentation
Computer vision – human tracking
Brox et al. 2007: 3D human pose tracking
Wedel et al. 2007: obstacle detection and segmentation
© 2007 Thomas Brox
Image
Processing
13
© 2007 Thomas Brox
Image
Processing
Computer vision – human tracking
14
Difference between image processing and computer vision
•
Usually, the term “image processing” is used for the general subject of
processing images with a computer
•
Computer vision signifies the specific task to make the computer interpret
the content of images
•
This is a difficult and so far unsolved task
•
Computer vision has similar motivations as artificial intelligence and
cognitive neuroscience
Brox et al. 2007: 3D human pose tracking
© 2007 Thomas Brox
15
© 2007 Thomas Brox
16
Image
Processing
Image
Processing
Why is computer vision difficult?
•
Vision is a natural and easy task for humans (and many animals)
•
This is not for free: ~50% of the primate’s cortex deals with the processing
of visual information (Felleman-van Essen 1991)
•
Making a computer see like
humans see means to solve
a large part of the AI problem
(this cannot be easy)
•
What do you see in this
image?
•
Images are only a structured grid of numbers
What’s that?
Author: Daniel Cremers
•
A lot of high level knowledge
and content information
necessary
© 2007 Thomas Brox
Image
Processing
17
•
This is how the computer sees Einstein
•
Demonstrates what our brain achieves at the unconscious level
© 2007 Thomas Brox
Image
Processing
Importance of the spatial arrangement
•
•
Image content is defined by the spatial arrangement of intensities
•
It is not sufficient to treat images as vectors and to analyze these vectors
Zebra image
© 2007 Thomas Brox
Importance of image processing and computer vision
Computer vision is a very young research field
– Main computer vision conference (ICCV) founded in 1987
– Main computer vision journal (IJCV) founded in 1988
Same image with a different
row length
•
Nonetheless, it belongs already to the most influential
subfields of computer science; tendency: growing rapidly
•
By 2006, the International Journal of Computer Vision
had the highest impact factor of all computer science
journals: 6.085
•
Impact factor in 2002: 2.03
•
Computer vision applications not restricted by a small
market but by the limited quality provided so far
•
19
18
More research Æ more products
© 2007 Thomas Brox
INT J COMPUT VISION 6.085
ACM T INFORM SYST 5.059
BIOINFORMATICS 4.894
MIS QUART 4.731
IEEE T PATTERN ANAL 4.306
ACM COMPUT SURV 4.13
ACM T GRAPHIC 4.081
J AM MED INFORM ASSN 3.979
IEEE T EVOLUT COMPUT 3.77
IEEE T MED IMAGING 3.757
NEUROINFORMATICS 3.541
J CHEM INF MODEL 3.423
VLDB J 3.289
MED IMAGE ANAL 3.256
J ACM 2.917
J CRYPTOL 2.833
IEEE T IMAGE PROCESS 2.715
MACH LEARN 2.654
IEEE T NEURAL NETWOR 2.62
IEEE WIREL COMMUN 2.577
COGNITIVE BRAIN RES 2.568
IEEE T MOBILE COMPUT 2.55
CHEMOMETR INTELL LAB 2.45
IEEE INTELL SYST 2.413
HUM-COMPUT INTERACT 2.391
J MOL GRAPH MODEL 2.371
J BIOMED INFORM 2.346
J COMPUT PHYS 2.328
DATA MIN KNOWL DISC 2.295
IEEE ACM T COMPUT BI 2.283
ARTIF INTELL 2.271
J MACH LEARN RES 2.255
NEURAL COMPUT 2.229
IEEE NETWORK 2.211
ACM T DATABASE SYST 2.143
COMPUT BIOL CHEM 2.135
IEEE T SOFTWARE ENG 2.132
INFORM MANAGE-AMSTER 2.119
QUANTUM INF COMPUT 2.105
J COMPUT AID MOL DES 2.089
IEEE T KNOWL DATA EN 2.063
IEEE PERVAS COMPUT 2.062
J COMPUT BIOL 2
MATCH-COMMUN MATH CO 2
NEURAL NETWORKS 2
Impact factors of
computer science
journals 2006
20
Image
Processing
•
•
Quality control, visual inspection
•
•
Fingerprint recognition
Iris recognition
Face recognition
Tracking
Medical systems
•
Entertainment industry
–
–
–
–
3D reconstruction
Motion capturing
Augmented reality
Human-machine interaction
•
Driver assistance systems
– Lane control
– Collision avoidance
– Autonomous driving
•
•
– Autonomous robots (e.g. pathfinder)
– Domestic robots
•
Artificial intelligence
21
Physics
– Optics
– Computational physics
•
Electrical engineering
– Signal processing
•
Neuroscience
– Neurophysiology
– Computational neuroscience
– Psychophysics
Numerics
Statistics
Linear algebra
Functional analysis
Graph theory
Geometric algebra
•
Medicine
•
Philosophy
© 2007 Thomas Brox
Image
Processing
Conferences and Journals
•
Mathematics
–
–
–
–
–
–
Robotics
Audio processing
Pattern recognition
Optimization
Machine learning
Data retrieval
Computer graphics
Robotics
Control theory
Software engineering
22
Overview (planned)
Conferences
–
–
–
–
–
–
–
–
•
•
Related sciences
Computer science
–
–
–
–
–
–
–
–
–
Earth surveillance
© 2007 Thomas Brox
Image
Processing
•
– Weather forecasts
– Google Earth
– Image enhancement
– Data analysis
– Routine diagnostics
•
Information systems
– Document analysis
– Image Google
Security systems
–
–
–
–
Image
Processing
Some image processing applications
ICCV:
ECCV:
CVPR:
NIPS:
DAGM:
ICIP:
ICPR:
SSVM:
International Conference on Computer Vision
European Conference on Computer Vision
Int. Conference on Computer Vision and Pattern Recognition
Neural Information Processing Systems
Tagung der Deutschen Arbeitsgemeinschaft für Mustererkennung
International Conference on Image Processing
International Conference on Pattern Recognition
Int. Conf. on Scale Space and Variational Methods
•
•
•
•
•
•
•
•
•
•
•
•
•
•
Journals
–
–
–
–
–
–
–
–
–
International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Image Processing
Computer Vision and Image Understanding
Image and Vision Computing
Journal of Mathematical Imaging and Vision
Journal of Visual Communication and Image Representation
Realtime Imaging
Pattern Recognition
© 2007 Thomas Brox
23
Class 1: Introduction
Class 2: Image acquisition and representation
Class 3: Noise, point operations
Class 4: Fourier transform
Class 5: Linear filters
Class 6: Wavelets
Class 7: Morphological filters
Class 8: Nonlinear diffusion filters
Class 9: Variational methods I
Class 10: Variational methods II
Class 11: Deconvolution
Class 12: Texture analysis and filtering
Class 13: Color spaces
Continued next term with the course Computer Vision
© 2007 Thomas Brox
24
Image
Processing
Image
Processing
Summary
•
Image processing, and particularly computer vision, are important
research fields
•
Their importance grows rapidly with the number of successful applications
•
Image processing makes use of techniques from various other sciences
•
Especially mathematics provides many helpful tools
© 2007 Thomas Brox
25
Literature
•
R. C. Gonzalez, R. E. Woods: Digital Image Processing, Addison-Wesley, Reading, 2nd
Edition, 2002.
•
J. Bigün: Vision with Direction, Springer, Berlin, 2006.
•
K. D. Tönnies: Grundlagen der Bildverarbeitung (in German), Pearson Studium, Munich,
2005.
•
CV Online: Online compendium on numerous image processing and computer vision topics,
http://homepages.inf.ed.ac.uk/rbf/CVonline/
© 2007 Thomas Brox
26