Transcript Slide 1
Digital Image Processing
Ligang Liu
Zhejiang University
[email protected]
Media
A picture is worth 1000 words…
A video is worth 1000 sentences…
Rich information from visual data
Examples of images around us
Natural photographic images
Artistic and engineering drawings
Scientific images (satellite, medical, etc.)
Motion picture –video
Movies, TV programs, news
Family video
Surveillance and highway camera
Why do we process images?
Enhancement and restoration
Transmission and storage
images from oversea via Internet, or from a remote
planet
Information analysis and automated recognition
remove artifacts and scratches from an old
photo/movie
improve contrast and correct blurred images
providing “human vision” to machines
Security and rights protection
encryption and watermarking
Why Digital?
“Exactness”
Convenient & powerful computer-aided processing
Perfect reproduction without degradation
Perfect duplication of processing result
Can perform rather sophisticated processing through hardware
or software
Even kindergartners can do it!
Easy storage and transmission
1 CD can store hundreds of family photos!
Paperless transmission of high quality photos through network
within seconds
Human Vision System
Image is to be seen.
Perceptual Based Image Processing
Focus on perceptually significant information
Discard perceptually insignificant information
Issues:
Biological
Psychophysical
Color
Color is the perceptual result of light
having wavelength 400 nm to 700 nm
that is incident upon the retina.
“Power distribution exists in the physical
world, but color exists only in the eye
and the brain.”
Does “red” mean the same to different
people?
Color Spectrum
Grassman's First Law of
Additive Color Mixture
Any color can be matched by a linear
combination of three other colors
(primaries, eg RGB), provided that none
of those three can be matched by a
combination of the other two.
C= Rc(R ) + Gc(G) + Bc(B)
Color Spaces
RGB
CMY
CIE XYZ
sl
Different Image Types
Binary images (0 or 1)
Gray images (0~255)
Color images
indexed color images
full color images (24 bits per pixel, 8-red,
8-green, 8-blue) )
A Binary Image
Gray Images
8 bits per pixel
Full Color Images
24 bits per pixel, and the three
channels R G B are three gray images
respectively
Color Components
Image Programming
class CImage
{
unsigned int width;
unsigned int height;
unsigned char *data;
};
Not difficult…
Related Fields
Imaging
Medical, remote sensing, weather
Computer vision
Computer graphics
Machine learning
Video processing
Related Math
Fourier analysis
Wavelet
Probability and statistics
PDE
Linear/nonlinear optimization
Machine learning
…
References
Journals
IEEE Transaction on Pattern Analysis and Machine
Intelligence (PAMI)
IEEE Transaction on Image Processing
IEEE Transaction on Signal Processing
IEEE Transaction on Circuits and System for Video
Technology
International Journal on Computer Vision (IJCV)
Pattern Recognition
Conferences
Graphics Conferences (Siggraph…)
Vision conferences: ICCV, ECCV, ACCV, CVPR
Course Information
Seminar
Grading
Report papers by yourselves
Seminar reports and final report
Course homepage and FTP
Objectives
Learn something interesting
Do something interesting
Find some interesting problems
Improve your abilities and experiences!
Requirements
Reporter
Audience
Over-prepared: read a series of important papers, PPT (texts
and images)
Professional: PPT, explaining, interaction…
List all references on the last slide
His own idea or own work
Challenging the reporter
Ask questions
Learn something new
Active and creative!
Q&A