KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
1
INTRODUCTION TO THE COURSE
KOM3212 Image Processing in Industrial
Systems
Some of the contents are adopted from
R. C. Gonzalez, R. E. Woods, Digital Image Processing, 2nd edition, Prentice Hall, 2008
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Today’s lecture
• Information about the course
• What is Image Processing ?
• What to learn?
• Applications
2
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Information about the course
Course Information
Instructor: Dr. Muharrem Mercimek
Office: A-216
Office Hours: Thursday 10:00-13:00,
Class Hours: Friday 10:00-11:50
Class Location: A-015
Group:1
Course Materials: http://www.yildiz.edu.tr/~mercimek
Email: [email protected], [email protected]
3
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
4
Information about the course
Textbook and course Materials
Main Text Book:
R. C. Gonzalez, R. E. Woods, Digital Image Processing, 2nd edition, Prentice Hall,
2008.
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
5
Information about the course
Grading
• Assignments:
• Class Attendance:
• Exams:
15%
10%
75%
Assignments
• There will be individual programming assignments and these will be listed on the
•
•
•
•
schedule page. Due dates will be specified and the students should submit their
material on time.
Program submissions should be the outcome of each student’s own endeavors.
Collaborative study is encouraged, but any code and document you prepare must be
your own.
Submissions must include source codes as well as the documentations and data files
when needed.
When submitting your Assignments via e-mail always zip it, and name it like
KOM3212_YourName_YourNumber_AssignmentNumber.{zip or rar}
When submitting an assignment always put a subject title relevant to why you are
sending it. You can use the name of your zip file again.
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Information about the course
• The most important policy you should follow up;
• Cell-phone use is prohibited during the class
6
7
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Information about the course
Week
Subjects
Preparation
1
Introduction
Textbook Ch1
2
Visual Perception and Image Formation
Textbook Ch2
3
Image Enhancement – in the Spatial Domain I
Textbook Ch3
4
Image Enhancement – in the Spatial Domain II
Textbook Ch3
5
Image Enhancement – in the Frequency Domain I
Textbook Ch4
6
Image Enhancement – in the Frequency Domain II
Textbook Ch4
7
Mid-term I
8
Image Restoration – Using filters
Textbook Ch5
9
Image Restoration – Geometric Transformation
Textbook Ch5
10
Color Models, Color image Processing
Textbook Ch6
11
Morphological Image Processing
Textbook Ch9
12
Mid-term II
13
Image Segmentation
Textbook Ch10
14
Representation and Description
Textbook Ch11
15
Final Exam
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
8
Information about the course
Programming environment
• The efforts in this course will involve quite good use of Linux and GNU Compiler
Collection (GCC). The basic materials to make the students familiar with GCC will be
provided. You may use any platform to develop your program; your final code can be
compiled and executed on Linux, as this will be the testing platform used by the
instructor.
Academic Honesty
• Any misconduct in this course is considered a serious offense and strong penalties will
be the results of such behaviors. It is cheating to copy others’ code. Fake program
outputs and documents is also considered as cheating.
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
9
WHAT IS IMAGE PROCESSING ?
Some of the contents are adopted from
R. C. Gonzalez, R. E. Woods, Digital Image Processing, 2nd edition, Prentice Hall, 2008
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
10
Image – bitmap representation
• image: Also called “raster or pixel maps” representation
• An image is broken up into a grid
• [, ] =
2 (+1) (+1)
(, ; )
0


representations of the practically
continuous scene related to CCD sensor
sizes.
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Image – bitmap representation
, 
Focal Plane
 ,  , 
, 
1 , 1 , 1
1 , 1


 , 
Perspective projection model for a pinhole
camera with a focal length of .
11
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
12
Image – vector representation
• Object-oriented vector representation
• No information of individual pixel, but information of an object (circle, line,
square, etc.)
• Can only represent simple line drawings (CAD), shapes, shadings, etc.
• Adv. Better representation of models, small size files
On the other hand for Bitmap Representation
• Images with complex variations in colors, shades, shapes.
• Larger image size
Line(xa1, ya1, xa2, ya2)
• Fixed resolution
Line(xb1, yb1, xb2, yb2)
Line(xc1, yc1, xc2, yc2)
Point(xc2, yc2)
Ellipse(xd1, yd1, rx1, ry1)
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
13
Why Image Processing?
• Images are very important.
• One image is worth more than ten thousands words – an important media
• But they are never as desired(quality, size, etc)
• Blur, Noise, Distortions, Color and contrast problems, etc.
• Applications of Image Processing
• Fingerprint retrieval
• Automatic target recognition
• Industrial inspection
• Medical imaging
and more …
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
14
Goals of image processing
• Image improvement
• Improving the visual appearance of images to a human viewer
• Image analysis
• Preparing images for measurement of the features and structures
present
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
15
What to learn?
Preprocessing – low level
Image Improvement
Image
Acquisition
Image
Enhancement
Image
Restoration
Image
Compression
Image
Coding
Shape
descriptors
Fourier/Wavelet
Analysis
Knowledge Base
High-level IP
Image Analysis
Image
Segmentation
Representation
& Description
Recognition &
Interpretation
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Image acquisition
• Video camera
• Infrared camera
• Range camera
• Line-scan camera
• Hyperspectral camera
• Omni-directional camera
• and more …
16
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
17
Light and Electromagnetic Spectrum
• Electromagnetic waves can be regarded as a stream of mass-less particles each
travelling in a wavelike pattern and moving at the speed of light
• Each particle contains a certain amount of energy
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
18
Light and Electromagnetic Spectrum
• Light is a particular type of electromagnetic radiation
• 0.43m-violet to about 0.79m-red
• For convenience 6 bands are used to name the light in the visible spectrum
• The colors that human perceive on an object is determined by the light it is
reflected from it.
• A body that reflects all of the light bands will be perceived as white to the
user. If a body favors specific band and reflects it that we see it having that
color.
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
19
Color Perception of Human Eye
• Humans do not have a sensor for each frequency of light
• Instead, rods and cones are employed.
• Cones focus on recognizing brighter light (photopic vision) with more
sensitivity about individual colors,
• Rods on dim lighting scenarios (scotopic vision) with less color sensitivity, and
a combination of the two for in-between lighting (mesopic vision).
• cones detect light along something resembling a gaussian curve. There are
three wavelengths at which the cones are centered, as shown
blog.triplelift.com
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
20
Imaging Sensors
An image sensor converts a optical image
into an electronic signal. It is used mostly
in imaging devices.
Today, most digital still cameras use either
a CCD image sensor or a CMOS sensor
Neither technology has a clear advantage
in image quality
CMOS sensors can potentially be
implemented with fewer components, use
less power
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
21
Color Images in Cameras
There are several main types of color
image sensors, differing by the type of
color-separation mechanism:
One of them is
Bayes filter sensor: An array of color filters
is used. Original light is separated to its
bands and the resulting patterns are
registered to form a single image,
en.wikipedia.org
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
A simple image formation model
• f(x,y): the intensity is called the gray level for monochrome image
• f(x, y) = i(x, y).r(x, y)
• 0 < i(x, y) < inf, the illumination (lm/m2)
• 0< r(x, y) < 1, the reflectance
• Some illumination figures (lm/m2)
• 90,000: full sun
• 10,000: cloudy day
• 0.1: full moon
• 1,000: commercial office
- 0.01: black velvet
- 0.93: snow
22
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Camera exposure
• ISO number
• Sensitivity of the film or the sensor
• Can go as high as 1,600 and 3,200
• Shutter speed
• How fast the shutter is opened and closed
• f/stop : the size of aperture
• 1.0 ~ 32
23
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Sampling and Quantization
24
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
An effect of under-sampling, aliasing
 Aliasing (the Moire effect)
www.wfu.edu/~matthews/misc/DigPhotog/alias/
25
26
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
1x
1/2 x
1/4 x
1/8 x
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Uniform quantization
• Digitized in amplitude (or pixel value)
• PGM – 256 levels  4 levels
255
192
3
2
128
64
0
1
0
27
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
28
Uniform quantization
Original
8 bits
4 levels (2 bits)
16 levels (4 bits)
2 levels (1 bit)
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Image resolution
• Spatial resolution
• Line pairs per unit distance
• Dots/pixels per unit distance
• dots per inch - dpi
• Intensity resolution
• Smallest discernible change in intensity level
• The more samples in a fixed range, the higher the resolution
• The more bits, the higher the resolution
29
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Applications
Histogram Equalization
www.mathworks.com
30
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
31
Applications
Color correction
Image Registration
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
32
Applications
target detection using an IR image,
and employing morphological operators
www.opticsinfobase.org
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
33
Applications
Point based operation - Thresholding
KOM3212 Image Processing in Industrial Systems | Dr Muharrem Mercimek
Applications
• OCR – optical character recognition, license plate recognition
www.microscan.com
34
Download

KOM3212 Image Processing in Industrial Systems Week 1