Lecture 0

An Introduction to
Digital Image Processing
& Computer Vision
Contents

This lecture will cover:

 What is a digital image?
 What is digital image processing?
 Examples of digital image processing
 What is computer vision?
 Example applications of computer vision
 Key stages in digital image processing
 Course outline and learning outcomes

Introduction to Image Processing 2

What Is a Digital Image?

 A digital image is a representation of a two-

dimensional image as a finite set of digital values,
called picture elements or pixels

Introduction to Image Processing 3

Digital Image

 Pixel values typically represent gray levels, colors.

 Remember digitization implies that a digital image is
an approximation of a real scene

1 pixel

Introduction to Image Processing 4

Binary Image

 Each pixel is just black (0) or white (1).

 We only need one bit per pixel.
 be suitable include text (printed or handwriting),
fingerprints, or architectural plans

Introduction to Image Processing 5

Gray-scale Image

 Each pixel is a shade of gray, normally from 0 (black)

to 255 (white).
 Each pixel can be represented by 8 bits (=1 byte)

Introduction to Image Processing 6

Color Image
 Each pixel has a particular colour, described by the
amount of red, green ad blue.

Introduction to Image Processing 7

What is Digital Image Processing ?
 Digital image processing deals with manipulation of
digital images through a digital computer.
• It is a subfield of signals and systems but focus
particularly on images.
 The main purpose of DIP is the visualization. The
improvement of the visual quality of the image for
human perception.

Introduction to Image Processing 8

Digital Image Processing
Digital image processing focuses on 3 major tasks:

 Improvement of pictorial information for human

interpretation
 Processing of image for autonomous machine
perception
 Processing of image data for efficient storage,
transmission

Introduction to Image Processing 9

Examples: Image Enhancement
 One of the most common uses of DIP techniques:
improve quality, remove noise etc

Introduction to Image Processing 10

Examples: Medicine
 Take slice from MRI scan of canine heart, and find
boundaries between types of tissue
• Image with gray levels representing tissue density
• Use a suitable filter to highlight edges

Original MRI Image of a Dog Heart Edge Detection Image

Introduction to Image Processing 11

What is Computer Vision ?
 Computer vision: The science and technology of
machines can see.
 Computer vision: make computers/machines
understand images and videos.

Introduction to Image Processing 12

Components of a Computer Vision System

Camera

Lighting

Computer

Scene

Scene Interpretation

Introduction to Image Processing 13

Examples: Law Enforcement
 Image processing techniques
are used extensively
by law enforcers
• Number plate recognition
for speed cameras/
automated toll systems
• Fingerprint recognition

Introduction to Image Processing 14

Examples: Human Computer Interfaces
 Try to make human computer interfaces more natural
• Face recognition
• Gesture recognition

Introduction to Image Processing 15

Examples: Smart Cars

 Mobileye [wiki article]

• Vision systems currently in high-end BMW, GM, Volvo
models. By 2010: 70% of car manufacturers.
Introduction to Image Processing 16
Examples: Google Cars

http://www.nytimes.com/2010/10/10/scienc
e/10google.html?ref=artificialintelligence

Introduction to Image Processing 17

Examples: Mobile Robots

NASA’s Mars Spirit Rover

http://en.wikipedia.org/wiki/Spirit_rover http://www.robocup.org/

Introduction to Image Processing 18

Examples: Fire and Smoke Detection

Introduction to Image Processing 19

Examples: Industrial Inspection
 Human operators are
expensive, slow
and unreliable
 Make machines do the
job instead
 Industrial vision systems
are used in all kinds
of industries

Introduction to Image Processing 20

Examples: PCB Inspection
 Printed Circuit Board (PCB) inspection
• Machine inspection is used to determine that all
components are present and that all solder joints are
acceptable
• Both conventional imaging and x-ray imaging

Introduction to Image Processing 21

Image Processing To Computer Vision
 The continuum from image processing to computer
vision can be broken up into low-, mid- and high-level
processes

Low Level Process Mid Level Process High Level Process

Input: Image Input: Image Input: Attributes Output:
Output: Image Output: Attributes Understanding
Examples: Noise Examples: Object Examples: Scene
removal, image recognition, understanding,
sharpening segmentation autonomous navigation

Introduction to Image Processing 22

Image Compression

 To reduce amount of data required to represent a

digital image with no significant loss of information.

Introduction to Image Processing 23

Key Stages in Digital Image Processing

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 24

Key Stages in Digital Image Processing:
Image acquisition

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 25

Key Stages in Digital Image Processing:
Image Enhancement

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 26

Key Stages in Digital Image Processing:
Image Restoration

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 27

Key Stages in Digital Image Processing:
Morphological Processing

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 28

Key Stages in Digital Image Processing:
Segmentation

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 29

Key Stages in Digital Image Processing:
Object Recognition
Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 30

Key Stages in Digital Image Processing:
Image Compression
Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 31

Key Stages in Digital Image Processing:
Colour Image Processing
Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Problem Domain

Colour Image Image

Processing Compression

Introduction to Image Processing 32

Course Outline

Lecture 1. Digital Image Fundamentals (week 1)

Lecture 2. Image Enhancement and Restoration (week 2,3)
Lecture 3. Morphological Image Processing (week 4,5)
Lecture 4. Image Segmentation (week 6,7)
Lecture 5. Image Representation & Description (week 8,9)
Lecture 6. Object (Pattern) Recognition (week 10,11)
Project presentation (week 12)
Lecture 7. Image Compression (week 13,14)
Review (week 15)

Introduction to Image Processing 33

Textbooks
R. C. Gonzalez, R. E. Woods, Digital
Image Processing, Addison Wesley,
2nd edition (2002), 3rd edition (2008).

R. C. Gonzalez, R. E. Woods, S. L.
Eddins, Digital Image Processing Using
Matlab, Gatesmark Publishing, 2nd
edition (2009)

Introduction to Image Processing 34

Prerequisites

 Signals and systems: Since DIP is a subfield of

signals and systems , so it would be good if you
already have some knowledge about signals and
systems, but it is not necessary. But you must have
some basic concepts of digital electronics.
 Calculus and probability: Basic understanding of
calculus , probability and differential equations is also
required for better understanding.
 Basic programming skills: Some of the basic
programming skills on any of the popular languages
such as Python or C++.

Introduction to Image Processing 35

Grading Schemes

 Homework+Quiz: 15% (maximum 4 students/group)

 Midterm exam: 10%
 Final exam: 60%
 Final project + presentation: 15% (maximum 4
students/group)

Introduction to Image Processing 36

Final Project

 Students can work in a group of 2 or 3 students

 Recommended topics:
• Apple classification
(https://www.youtube.com/watch?v=eFu4F-2ly2c )
• Automatic inspection for bottles
(https://www.youtube.com/watch?v=Lx7nM6YEPeQ )
 Students can propose another topic but it must be
approved by the lecturer.
 Submit your Python/C code+final project report (week
11)
 Final presentation and demo in class (week 12)

Introduction to Image Processing 37

Learning Outcomes

 Understand basic image operations: image

enhancement, filtering techniques in spatial and
frequency domain, the image morphology and
segmentation concepts, image compression.

 Develop some basic applications for image processing

and computer vision such as simple automated
inspection systems, number plate recognition, face
recognition applications

Introduction to Image Processing 38

Summary

We have looked at:

 What is a digital image?

 What is digital image processing?
 What is computer vision?
 State of the art examples of digital image processing
and computer vision.
 Key stages in digital image processing.
 Course contents, grading schemes, and learning
outcomes.

Introduction to Image Processing 39