The document discusses a computer vision workshop that covered topics including what a digital image is, what digital image processing is, examples of digital image processing, and key stages in digital image processing. It defines a digital image as a finite set of pixels representing properties like gray levels or color. Digital image processing focuses on improving images for interpretation and processing images for storage, transmission and machine perception. Examples covered include image enhancement, medical imaging, geographic information systems, law enforcement, and object segmentation. Key stages discussed include image acquisition, restoration, enhancement, representation and description, segmentation, and compression.

1. 4th Computer Vision Workshop
February 2011

2. Introduction to Image Processing
What is a digital image?
What is digital image processing?
Usage examples of digital image processing
Key stages in digital image processing

3. Introduction to Image Processing
What is a digital image?
What is digital image processing?
Usage examples of digital image processing
Key stages in digital image processing

4. 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

5. What is a Digital Image? (cont…)
 Pixel values typically represent gray levels, colours,
heights, opacities etc
 Remember digitization implies that a digital image is
an approximation of a real scene
1 pixel

6. What is a Digital Image? (cont…)
 Common image formats include:
 1 sample per point (B&W or Grayscale)
 3 samples per point (Red, Green, and Blue)
 4 samples per point (Red, Green, Blue, and “Alpha”,
a.k.a. Opacity)

7. Introduction to Image Processing
What is a digital image?
What is digital image processing?
Usage examples of digital image processing
Key stages in digital image processing

8. What is Digital Image Processing?
Digital image processing focuses on two major tasks
 Improvement of pictorial information for human
interpretation
 Processing of image data for storage, transmission and
representation for autonomous machine perception
Some argument about where image processing ends
and fields such as image analysis and computer vision
start

9. What is Digital Image Processing? (cont…)
The continuum from image processing to computer
vision can be broken up into low-, mid- and high-level
processes
Low Level Process
Input: Image
Output: Image
Examples: Noise
removal, image
sharpening
Mid Level Process
Input: Image
Output: Attributes
Examples: Object
recognition,
segmentation
High Level Process
Input: Attributes
Output: Understanding
Examples: Scene
understanding,
autonomous navigation

10. Introduction to Image Processing
What is a digital image?
What is digital image processing?
Usage examples of digital image processing
Key stages in digital image processing

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

12. denoise
Examples: Image Enhancement

13. deblur
Examples: Image Enhancement

14. 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

15. Examples: GIS
Geographic Information Systems
 Digital image processing techniques are used extensively
to manipulate satellite imagery
 Terrain classification
 …

16. Examples: Law Enforcement
Image processing
techniques are used
extensively by law
enforcers
 Number plate
recognition for speed
cameras/automated toll
systems
 Fingerprint recognition
 Enhancement of CCTV
images

17. Examples: HCI
Try to make human
computer interfaces more
natural
 Face recognition
 Gesture recognition
These tasks can be
extremely difficult

18. Examples: Object Segmentation

19. Introduction to Image Processing
What is a digital image?
What is digital image processing?
Usage examples of digital image processing
Key stages in digital image processing

20. Key Stages in Digital Image Processing
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

21. Key Stages in Digital Image Processing:
Image Acquisition
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

22. Key Stages in Digital Image Processing:
Image Enhancement
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

23. Key Stages in Digital Image Processing:
Image Restoration
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

24. Key Stages in Digital Image Processing:
Morphological Processing
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

25. Key Stages in Digital Image Processing:
Segmentation
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

26. Key Stages in Digital Image Processing:
Object Recognition
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

27. Key Stages in Digital Image Processing:
Representation & Description
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

28. Key Stages in Digital Image Processing:
Image Compression
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

29. Key Stages in Digital Image Processing:
Colour Image Processing
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

30. Thresholding
 Use a threshold to transforms an input image
into a binary image
 Compare each input pixel value f(i, j) against
the threshold, θ, and setting the output pixel
value g(i, j) appropriately
0 if ( , )
( , )
1 otherwise
f i j
g i j

 


31. Thresholding
Dr. Philip Tse Multimedia Coding and Processing 31
 Sample black and white
images
θ=141 θ=128 θ=115

32. Thresholding
 Different images can be
generated from using different
thresholds.
 Higher threshold allows only
fewer brighter pixels to become
white.

33. Thresholding
 Many applications in image processing
 Difficult to decide the value of threshold, θ.
 The threshold value may depend on the application
required.

34. Summary
 We have looked at:
 What is a digital image?
 What is digital image processing?
 Usage examples of digital image processing
 Key stages in digital image processing
 Next section we will talk about OpenCV

36.  Introduction
 Getting Started
 Architecture & Modules
 Sample Code
OpenCV

37.  Introduction
 Getting Started
 Architecture & Modules
 Sample Code
OpenCV

38.  Open Source Computer Vision Library
 Originally developed by Intel, currently maintained by
Willow Garage
 Written in C/C++
 Implements Image Processing and Computer Vision
algorithms
OpenCV - Introduction

39.  Cross-platform and extremely portable
 Free!
 Targeted for real-time applications
OpenCV - Introduction

40.  Introduction
 Getting Started
 Architecture & Modules
 Sample Code
OpenCV

41. http://sourceforge.net/projects/opencvlibrary/files/opencv-win/2.1/

42.  Introduction
 Getting Started
 Architecture & Modules
 Sample Code
OpenCV

43.  CvAux
 Defunc areas and experimental algorithms
 IPP
 High Performance low-level routines if IPP is present
OpenCV – Architecture & Modules

44.  HighGUI
 “Smart” windows
 Image I/O, rendering
 Processing keyboard and other events, timeouts
 Trackbars
 Mouse callbacks
 Video I/O
OpenCV – Architecture & Modules

45.  Introduction
 Getting Started
 Architecture & Modules
 Sample Code
OpenCV

46.  Example code: load an image from disk and display it
on the screen
#include “highgui.h”
int main( int argc, char **argv )
{
IplImage *img = cvLoadImage( argv[1] );
CvNamedWindow(“Example1”, CV_WINDOW_AUTOSIZE);
cvShowImage(“Example1”, img);
cvWaitKey(0);
cvReleaseImage( &img );
cvDestroyWindow(“Example1”);
}
OpenCV – Sample Code