Professional Documents
Culture Documents
Course objectives
To give a thorough understanding of advance tools,
algorithms and techniques used in image processing to
the students
To enable students to be able solve an image processing
problem and to design systems on their own by giving
them hands on working experience on image processing
tools
To introduce advanced topics in image processing and
invoke interest for doing research in this field
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 2
1
Pre-requisites for the course
1. Knowledge of probability and random variables,
Vectors and Matrices.
2. Working knowledge of Matlab
3. Signals and Systems, and DSP courses especially the
concepts of Convolution, FFT, filtering, etc.
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 3
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 4
2
Assignments
Please check the class folder every day, for notification of
assignments, projects and updated information.
Assignments will have ~12% weight in the total marks.
Assignments may be written assignments of programming
assignments.
There will be a total of around 8 assignments.
The deadline for the submission of assignment will be given with
the assignment.
Assignments submitted after the deadline will not be accepted and
will carry ZERO MARKS.
Cheated assignments will get NEGATIVE MARKS.
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 5
Project
Projects will have ~15% weight in the total marks.
Projects may be conducted individually or in groups of two
students.
Different suggested topics for projects will be uploaded on the
class yahoo group within the first two weeks of the course. If you
want to do your own project take permission first.
Reading material and other sources for every project to help the
students will also be given.
Project topics should be selected and approved within the first five
weeks of the course.
Project presentation date will be announced and projects will not
be accepted after the presentation date.
Projects consisting of Downloaded codes or presentations will not
be accepted will carry ZERO MARKS.
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 6
3
Why do we process images?
Facilitate picture storage and transmission
– Efficiently store an image in a digital camera
– Send an image through mobile phone
Enhance and restore images
– Remove scratches from an old photo
– Improve visibility of tumor in a radiograph
Extract information from images
– Measure water pollution from aerial images
– Measure the 3D distances and heights of objects from stereo images
Prepare for display or printing
– Adjust image size
– Halftoning
Biometrics based identification
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 7
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 8
4
Image Processing Examples
Photo colorization
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 9
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 10
5
Image Enhancement
Initial image Final image
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 12
6
Image Processing Examples
Extraction of settlement area from an aerial image
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 13
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 14
7
Image Processing Examples
Medical Imaging: Computer Tomography (CT)
– Generating 3-D images from 2-D slices.
– CAD, CAM applications
– Industrial inspections
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 15
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 16
8
Image Processing Examples
Medical Imaging: Ultrasound imaging
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 17
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 18
9
Image Processing Examples
Image compression
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 19
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 20
10
Image Processing Examples
Face detection
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 21
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 22
11
Image Processing Examples
Face Morphing
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 23
X X
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 24
12
Personal Identification using Iris Recognition
1983 2000
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 26
13
Applications of DIP
Categorization according to image sources
Electromagnetic (EM) band Imaging
– Gamma ray images
– x-ray band images
– ultra-violet band images
– visual light and infra-red images
– Imaging based on micro-waves and radio waves
Non-EM band Imaging
– Acoustic and ultrasonic images
– Electron Microscopy
– Computer-generated synthetic images
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 27
EM Spectrum
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 28
14
Applications of DIP: EM band imaging
Gamma-ray imaging
– Nuclear medicine, astronomical observations.
X-ray Imaging
– Medical diagnostics (CAT scans, x-ray scans), industry, astronomy.
Ultra-violet imaging
– Fluorescence microscopy, astronomy,
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 29
Synthetic imaging
– 3D modeling or visualization systems for flight simulators, machine design,
special effects and animations,etc.
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 30
15
Classification of DIP and Computer Vision Processes
Image acquisition
Imaging
Digitization, quantization and
compression
Enhancement and restoration Image Processing
Image segmentation Imaging Analysis
Feature selection/extraction (Computer Vision and
Pattern recognition)
Image representation
Image understanding
Image interpretation
(Computer Vision and
Pattern recognition)
Physical action
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 32
16
Image Processing Computer vision and PR
Image acquisition by sensor Image Geometrical Rectification
Image sampling and quantization Camera geometry
Computer Vision
Feature Extraction
Image enhancement and restoration Edge and Interest points detection
Filtering in spatial domain or Texture and shading
frequency domain Shape from texture and shading
Feature Extraction Calculation on Multiple Views
Edge detection Multi-view geometry and Stereo imaging
Interest points Structure from motion
Colored image Processing Segmentation
Pseudo coloring Impose some order on group of pixels to
Color segmentation separate them from each other
Multi-resolution analysis Template matching
Pattern Recognition
Pyramids
Wavelets Segmentation
Other transformations Classification and Recognition
Image and video compression Classification and interpretation of objects
Image compression standards based on selected features
Video compression standards Recognize objects using probabilistic
techniques
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 33
Image sampling
Image restoration
– Noise reduction techniques
– Geometric transformations
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 34
17
Scope of DIP Course (continued)
Color image processing
– Color models
– Pseudocolor image processing
– Color transformations and color segmentation
Image compression
– Image compression models
– Error free compression
– Lossy compression, etc
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 35
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 36
18
Image Acquisition
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 37
sampling sampling
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 38
19
Sampling and Quantization
Sampling: Digitization of the spatial coordinates (x,y)
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 39
. . . . . .
. . . . . .
. . . . . .
f ( M 1,0) f ( M 1,1) . . . f ( M 1, N 1)
N : No of Columns
M : No of Rows
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 40
20
Digital Images
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 41
Sampling
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 42
21
Sampling
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 43
22
RGB (color) Images
Image acquisition
Line sensor
Array sensor
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 46
23
Image acquisition
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 47
Image acquisition
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 48
24
Digital Camera Technologies
CCD (Charge Coupled Device)
– Capacitive device
– Proper mechanism for charge
transfer
CMOS (Complementary magnetic
oxide)
– Fabricated in standard
semiconductor production line
– Lower power consumption A CCD:
2–5 W, CMOS: 20–50 mW
Foveon X3
– a chip of transparent quartz
containing 3 layers of CMOS
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 49
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 50
25
Digital Camera Technologies
CCD Array Cameras
Frame Transfer
Architecture
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 51
Interline Transfer
Architecture
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 52
26
Digital Camera Technologies
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 53
27
Acquisition of color images
Single sensor assembly
For still scenes
Three sensors
with prisms
Sensor arrays
a. Stripe filter pattern
b. Bayers filter pattern
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 55
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 56
28
Foveon X3 imager
A recent development in
photo-sensing technology
This sensor uses 3 layers of
CMOS imagers.
Each layer absorbs different
colours of light at different
depths.
Single shot camera for three
colors
Foveon has failed to make a
serious impact on the
market.
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 57
Scanning Schemes
Interlaced scanning
(used in TV)
Read/display all
even-numbered lines
(even field, half-size)
Restart
Read/display all odd-
A typical Interlaced Scanning scheme
numbered lines (odd
field, half-size)
Stitch the even and
odd fields together
and form a single,
full-size frame
Output
2/16/2016 theUniversity
Capital full-sizeof Science and Technology Advanced Digital Image Processing EE5623 58
frame
29
Interlaced scanning
When motion is present the interlaced scanning produces blurring
in the image
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 59
Scanning Schemes
Progressive Scanning
Immediately transfer an entire frame at once from
the image sensor without performing any line-
interlacing.
Suitable for fast motion detection applications
Incompatible with standard television systems.
Popular in digital cameras (computer applications)
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 60
30
Various commercial sensor sizes
2/16/2016 Capital University of Science and Technology Advanced Digital Image Processing EE5623 61
31