Chapter One
Introduction to Computer Vision and
Image Processing
Computer Vision 1- Introduction to Computer Vision
1-1
Computer Vision
Computer Vision is :
◆ the substitution of the human visual sense and judgment capabilities
with a video camera and computer to perform an inspection task.
◆ the automatic acquisition and analysis of images to obtain desired
data for controlling or evaluating a specific activity.
◆ process that produces useful description to the viewer from images
of the external world.
◆ Construction of explicit, meaningful descriptions of physical objects
from images.
Computer Vision 1- Introduction to Computer Vision
1-2
Computer Vision
Computer vision studies the tools and theories that enable the design
of machines that can extract useful information from images and
videos toward the goal of interpreting the world.
Computer Vision 1- Introduction to Computer Vision
1-3
Computer Vision
The goal of computer vision is to develop algorithms that
allow computers to “see”.
Although vision is easy for people, it is difficult for
computers.
Computer Vision is sometimes called:
◆ Image Understanding
◆ Image Analysis
◆ Machine Vision
Computer Vision 1- Introduction to Computer Vision
1-4
Why we study Computer Vision?
Images and movies are everywhere
The need for understanding of human vision
Fast-growing collection of useful applications
Computer Vision 1- Introduction to Computer Vision
1-5
Application of CV
Fast-growing collection of useful applications of CV:
◆ Automated surveillance
◆ Face recognition and biometrics
◆ Obstacle avoidance
◆ Object recognition
◆ Autonomous driving
◆ Cartography( Maps from aerial and satellite images)
◆ Space science(planetary exploration)
◆ Medicine (pathology, surgery, diagnosis)
◆ Remote Sensing
◆ Industrial inspection
◆ Robotic control
Computer Vision 1- Introduction to Computer Vision
1-6
Related Fields in CV
AI
Computer Image
Graphics Processing
Computer
Vision
Pattern
Robotics
Recognition
Computer Vision 1- Introduction to Computer Vision
1-7
Why it is difficult?
An image is a two-dimensional optical projection, but the
world we wish to make sense of visually is three-
dimensional.
◆ We need to invert the 3D→ 2D projection in order to recover
world properties (object properties)
◆ But the 2D →3D inversion is mathematically impossible
Computer Vision 1- Introduction to Computer Vision
1-8
What is an Image?
Computer Vision 1- Introduction to Computer Vision
1-9
A Simple Image Formation Model
• A 2-D light-intensity function f(x,y): The value of f at
(x,y) the intensity (brightness) of the image at that point
0 < f(x,y) <
• The value or amplitude of f at spatial coordinates (x,y)
gives the intensity (brightness) of the image at that point.
• A Simple Image Model Illumination & reflectance components:
• llumination: i(x,y)
• Reflectance: r(x,y)
• Then, f(x,y) = i(x,y) r(x,y)
Where 0 < i(x,y) < and 0< r(x,y) < 1 (from total absorbassion to total
reflectante).
• Intensity of a monochrome image f at (xo,yo): gray level l of the image
at that point l=f(xo, yo), where Lmin ≤ l ≤ Lmax such that Lmin:
positive, Lmax: finite.
▪ Some Typical Ranges of Reflectance: 0.01 for black velvet, 0.65 for stainless steel, 0.80 for
flat-white wall paint, 0.90 for silver-plated metal, 0.93 for snow.
Computer Vision 1- Introduction to Computer Vision
1-10
Image formation (cont’d)
There are two parts to the image formation process:
(1) The geometry, which determines where in the image plane the
projection of a point in the scene will be located.
(2) The physics of light, which determines the brightness of a point in
the image plane.
► Simple model:
f(x,y) = i(x,y) r(x,y)
i: illumination, r: reflectance
• As light is a form of energy, f(x,y) must be non zero and finite.
Computer Vision 1- Introduction to Computer Vision
1-11
Challenges: Face Recognition
Which two pictures show the same person?
◆ Most algorithms for computer vision select 1 and 2 as the same
person, since those images are more similar than 1 and 3.
Computer Vision 1- Introduction to Computer Vision
1-12
Challenges: Object intra-class variation
Computer Vision 1- Introduction to Computer Vision
1-13
Challenges: illumination
Computer Vision 1- Introduction to Computer Vision
1-14
Challenges: Activity Understanding
Computer Vision 1- Introduction to Computer Vision
1-15
Challenges: Activity Understanding
Computer Vision 1- Introduction to Computer Vision
1-16
State of the art examples of digital image processing
Optical character recognition (OCR)
• Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software
Digit recognition, AT&T labs License plate readers
http://www.research.att.com/~yann/ http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
Computer Vision 1- Introduction to Computer Vision
1-17
Face Detection
• Many new digital cameras now detect faces
– Canon, Sony, Fuji, …
Computer Vision 1- Introduction to Computer Vision
1-18
Smile Detection
Computer Vision 1- Introduction to Computer Vision
1-19
Object Recognition (in supermarkets)
LaneHawk by EvolutionRobotics
“A smart camera is flush-mounted in the checkout lane, continuously
watching for items. When an item is detected and recognized, the cashier
verifies the quantity of items that were found under the basket, and
continues to close the transaction. The item can remain under the basket,
and with LaneHawk,you are assured to get paid for it… “
Computer Vision 1- Introduction to Computer Vision
1-20
Vision-based Biometrics
“How the Afghan Girl was Identified by Her Iris Patterns”
Computer Vision 1- Introduction to Computer Vision
1-21
Login without a password…
Face recognition systems now
Fingerprint scanners on
beginning to appear more widely
many new laptops, http://www.sensiblevision.com/
other devices
Computer Vision 1- Introduction to Computer Vision
1-22
Object Recognition (in mobile phones)
Point & Find, Nokia
Google Goggles
Computer Vision 1- Introduction to Computer Vision
1-23
Special effects: shape capture
The Matrix movies, ESC Entertainment, XYZRGB, NRC
Computer Vision 1- Introduction to Computer Vision
1-24
Special effects: Motion Capture
Pirates of the Carribean, Industrial Light and Magic
Computer Vision 1- Introduction to Computer Vision
1-25
Sports
Computer Vision 1- Introduction to Computer Vision
1-26
Smart Cars
• Mobileye
– Vision systems currently in high-end BMW, GM,
Volvo models
– By 2010: 70% of car manufacturers.
Computer Vision 1- Introduction to Computer Vision
1-27
Google cars
Computer Vision 1- Introduction to Computer Vision
1-28
Interactive Games: Kinect
• Object Recognition:
http://www.youtube.com/watch?feature=iv&v=fQ59dXOo6
3o
• Mario: http://www.youtube.com/watch?v=8CTJL5lUjHg
• 3D: http://www.youtube.com/watch?v=7QrnwoO1-8A
• Robot: http://www.youtube.com/watch?v=w8BmgtMKFbY
Computer Vision 1- Introduction to Computer Vision
1-30
Vision in space
NASA'S Mars Exploration Rover Spirit captured this westward view from atop
a low plateau where Spirit spent the closing months of 2007.
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.
Computer Vision 1- Introduction to Computer Vision
1-31
Industrial Robots
Vision-guided robots position nut runners on wheels
Computer Vision 1- Introduction to Computer Vision
1-32
Mobile Robots
NASA’s Mars Spirit Rover
http://en.wikipedia.org/wiki/Spirit_rover http://www.robocup.org/
Saxena et al. 2008
STAIR at Stanford
Computer Vision 1- Introduction to Computer Vision
1-33
Medical Imaging
Image guided surgery
3D imaging
Grimson et al., MIT
MRI, CT
Computer Vision 1- Introduction to Computer Vision
1-34
Human Activity Recognition
Computer Vision 1- Introduction to Computer Vision
1-35
Medical Applications
Skin cancer Breast cancer
Computer Vision 1- Introduction to Computer Vision
1-36
Key Stages of Digital Image Processing
Key steps of image processing
Computer Vision 1- Introduction to Computer Vision
1-37
Step 1: Image Acquisition
▪ Digital imaging or digital image acquisition is the
creation of a representation of the visual
characteristics of an object, such as a physical scene
or the interior structure of an object.
Computer Vision 1- Introduction to Computer Vision
1-38
Cont’d…
• In image processing, it is defined as the action of
retrieving an image from some source, usually a
hardware-based source for processing.
• It is the first step in the workflow sequence
because, without an image, no processing is
possible.
• The image that is acquired is completely
unprocessed.
• In image acquisition using pre-processing such
as scaling is done.
Computer Vision 1- Introduction to Computer Vision
1-39
Step 2: Image Enhancement
It is the process of adjusting digital images so that the results
are more suitable for display or further image analysis.
Usually in includes sharpening of images, brightness &
contrast adjustment, removal of noise, etc.
In image enhancement, we generally try to modify the image,
so as to make it more pleasing to the eyes.
It is subjective in nature as for example some people like high
saturation images and some people like natural color. That's
why it is subjective in nature as it differs from person to
person.
Computer Vision 1- Introduction to Computer Vision
1-40
Step 3: Image Restoration
It is the process of recovering an image that has been
degraded by some knowledge of degraded function H and
the additive noise term.
Unlike image enhancement, image restoration is
completely objective in nature.
Computer Vision 1- Introduction to Computer Vision
1-41
Step 4: Color Image Processing
This stage handles the image processing of colored
images either as indexed images or RGB images.
Computer Vision 1- Introduction to Computer Vision
1-42
Step 5: Wavelets and multiresolution
processing
• Wavelets are small waves of limited duration which
are used to calculate wavelet transform which
provides time-frequency information.
• Wavelets lead to multiresolution processing in
which images are represented in various degrees of
resolution
Computer Vision 1- Introduction to Computer Vision
1-43
Step 6: Compressions
Compression deals with the techniques for reducing the
storage space required to save an image or the bandwidth
required to transmit it.
This is particularly useful for displaying images on the
internet as if the size of the image is large, then it uses more
bandwidth (data) to display the image from the server and
also increases the loading speed of the website.
Computer Vision 1- Introduction to Computer Vision
1-44
Step 7: Morphological processing
It deals with extracting image components that are useful
in representation and description of shape.
It includes basic morphological operations like erosion and
dilation.
45
Computer Vision 1- Introduction to Computer Vision
1-45
Step 8: Segmentations
It is the process of partitioning a digital image into multiple
segments.
It is generally used to locate objects and boundaries in
objects.
Computer Vision 1- Introduction to Computer Vision
1-46
Step 9: Representations and Descriptions
• Representation deals with converting the data into a
suitable form for computer processing.
• Boundary representation: it is used when the focus is on external
shape characteristics e.g. corners
• Regional representation: it is used when the focus in on internal
properties e.g. texture.
• Description deals with extracting attributes that
• Results in some quantitative information of interest
• is used for differentiating one class of objects from others
12/16/2022
Computer Vision 1- Introduction to Computer Vision
1-47
Step 10: Object Recognitions
▪ It is the process that assigns a label (e.g. car) to an object
based on its description.
Computer Vision 1- Introduction to Computer Vision
1-48
Popular Image Processing Softwares
• CVIP tools (Computer Vision and Image Processing tools)
• Intel Open Computer Vision Library
• Microsoft Vision SDL Library
• KHOROS
• ImageJ
• MATLAB
• Python
• OpenCV
Computer Vision 1- Introduction to Computer Vision
1-49
Lab-I
Take satellite image from google, and use a python code to:
1. Change into matrix form in different dimensions
2. Show the quality of the image in different pixel and bit
sizes
3. Apply different noise removal technique to show quality
of the image
4. Apply different transforming techniques
Computer Vision 1- Introduction to Computer Vision
1-50