1. 1
Computer Imaging
Digital Image Processing
Computer Vision
Introduction
“One picture is worth more than ten thousand words”
2. 2
Computer Imaging
Image analysis involves examination of image
data to facilitate solving an imaging problem
A computer vision application can be
considered to be a deployed image analysis
system
In a computer vision system the images are
intended to be “seen” by a computer
3. 3
Image Processing Computer Vision
Input Image
Output Image (for human
consumption)
Topics
Image restoration
Image enhancement
Image compression
Image morphing, etc.
Input Image
Output Image attributes (for
computer use)
Topics
Image segmentation
Image recognition (feature
extraction)
Motion analysis & tracking
3D shape reconstruction, etc.
Computer Imaging
Computer Imaging can be separated into two different but
overlapping areas:
4. 4
Digital images:
A pixel has a location (the spatial coordinate) and a
value.
Digital images can be from many types of sources.
Digital image processing
Digital image processing is closely related to
signal processing at one end, and to computer
vision at the other end.
Digital Image Processing (DIP)
5. 5
Computer vision is concerned with making
computers “understand” what is contained in an
image and other functions of human vision.
It is sometimes considered to be a topic of artificial
intelligence.
However, it is not possible to state exactly where
image processing ends and computer vision begins.
If you compare a digital image processing book
and a computer vision book, you will find a lot of
overlap.
Computer Vision
7. 7
Why DIP?
Hospitals (Medical Imaging: Radiology - MRI, CT Scan, X-Rays, Ultrasound, Retinopathy
and other Pathologies)
Forensic Departments (like Punjab Forensic Science Agency: Firearms identification, lab. tests,
Image & video forensics)
Software Houses (Games developments including Kinect, Touch applications)
Electronic & Print Media (Artistic effects, Morphology)
Security Agencies, Industries & Offices (Biometrics, Surveillance, Object & Speed
recognition)
Pakistan Air Force & NESCOM (UAV: drone project with NESCOM)
GIS (SUPARCO: Satellite Imagery; Terrain Classification; Meteorology; Weather)
OCR (text, number plate recognitions etc.)
MRD (Multidisciplinary Research & Development)
8. 8
Defect Detection in Microdisplay Chips
Captured
image
After
defect
detection
After blob
analysis
Inspection speed vastly increased
Much lower error rates
More complete analysis
Cost savings
9. 9
Image Processing
Computer imaging application involving a
human being in the visual loop
Consists of following major fields:
o Image enhancement
o Image restoration
o Image compression
14. 14
1. Computer Aided Inspection of Grains
2. Capturing outlines of planar images
3. Background adjustment of a digital photograph
4. Area of an irregular image
5. Traffic signal alert
6. Safe drive alert
7. Transformation and restoration of B &W photograph into fine &
colored picture
8. Enhancement of satellite images taken in cloudy area
9. Computer Aided Automatic Grading of Physical Models
10. Image & video compression
11. Image audio transformation system for blind people
12. Diabetes retinopathy on digital fundus images
13. Firearm identification
Industrial & Research Projects
15. 15
MRI brain images classification
Classification of brain MRI images using LDyWT (Lifting
Dyadic Wavelet Transform), Genetic algorithms, and SVM.
Denoising Medical Images
To investigate for a denoising method for medical images using
dyadic wavelet transform (DyWT) and one-dimensional
singularity function model.
Blood Vessel Segmentation in Retinal Images
To investigate for blood vessel segmentation method in retinal
images using A Generative Model for Image Segmentation
Based on Label Fusion
Industrial & Research Projects
18. 18
Can computers match (or beat) human vision?
Yes and no (but mostly no!)
humans are much better at “hard” things
computers can be better at “easy” things
19. 19
Why Study Computer Imaging?
Millions of images being captured all the time
Lots of useful applications
The next slides show the current state of the art
20. 20
Optical character recognition (OCR)
Digit recognition, AT&T labs
http://www.research.att.com/~yann/
Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software
License plate readers
http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
25. 25
Login without a password…
Fingerprint scanners on
many new laptops,
other devices
Face recognition systems now
beginning to appear more widely
http://www.sensiblevision.com/
26. 26
Object recognition (in mobile phones)
This is becoming real:
Microsoft Research
Point & Find, Nokia
27. 27
Earth viewers (3D modeling)
Image from Microsoft’s Virtual Earth
(see also: Google Earth)
30. 31
Vision-based interaction (and games)
Nintendo Wii has camera-based IR
tracking built in. See Lee’s work at
CMU on clever tricks on using it to
create a multi-touch display!
Digimask: put your face on a 3D avatar.
“Game turns moviegoers into Human Joysticks”, CNET
Camera tracking a crowd, based on this work.
31. 32
Vision in space
Vision systems (JPL) used for several tasks
• Panorama stitching
• 3D terrain modeling
• Obstacle detection, position tracking
• For more, read “Computer Vision on Mars” by Matthies et al.
NASA'S Mars Exploration Rover Spirit captured this westward view from atop
a low plateau where Spirit spent the closing months of 2007.
34. 35
Current state of the art
You just saw examples of current systems.
Many of these are less than 5 years old
This is a very active research area, and rapidly changing
Many new apps in the next 5 years
To learn more about imaging applications and companies
David Lowe maintains an excellent overview of
vision companies
http://www.cs.ubc.ca/spider/lowe/vision.html
35. 36
Objectives
To familiarize you with the basic techniques and
terminology of Computer Imaging
To provide the sufficient background for FYPs on
computer imaging
To ready you for learning the advanced topics of
Computer Imaging course at post graduate level, like
wavelets, camera models and calibration, motion
analysis and tracking, video understanding, image
mosaics, 3D-shape reconstruction, etc.
To excite & stimulate you!