CIS303 Advanced Forensic Computing

1
CIS303Advanced Forensic Computing

• Dr Giles Oatley

2
Image Analysis

• Introduction
• Greyscale images
• Colour images (RGB, HSV, indexed)
• Image representation in MatLab

3
Useful texts

• Digital Image Processing
• Rafael Gonzalez Richard Woods, Prentice Hall,
  (2e) 2002.
• ISBN 0-13-094650-8
• Covers the material in some depth, with
  significant mathematical content.
• There is also a Matlab-specific version Digital
  Image Processing Using Matlab
• Digital Image Processing, a practical
  introduction using Java
• Nick Efford, Addison Wesley, 2000. ISBN
  0-201-59623-7
• A very readable introduction which covers most of
  the material in a non-mathematical way.

4
Image Basics The pixel

• The basic unit of a digital image is the the
  pixel.
• The pixel shape in computer images is normally
  square or rectangular but, in principle, any
  cross section or size is possible. For example
  newspaper images are base on a variable sized
  pixel.
• The variable size is to compensate for having
  only two colours !

5
Digital image representation

• An image can be defined as a 2D finction f(x, y),
  where x and y are spatial coordinates, and the
  amplitude of f at any pair of coordinates (x, y)
  is called the intensity of the image at that
  point.
• An image is said to be of size (M x N), where
  (0,0) is the top left hand corner, (0,1) the next
  pixel in the top row etc.
• In Matlabs IPT, however, we denote (x, y) by (r,
  c) and coordinates start at (1,1) (r ranges from
  1 to M, c from 1 to N)

6
Greyscale images

• The standard greyscale image uses 256 shades of
  grey from 0 (black) to 255 (white).

7
Images as matrices

• The coordinate system given on a previous slide
  lead to the following representation of a digital
  image in Matlab
• The following data classes are used in Matlab to
  represent images

8
Colour images

• With colour images the situation is more complex.
  For a given number of pixels, considerably more
  data is required to represent the image and more
  than one colour model is used.
• We will consider only three of the more common
  colour models
• RGB (Red Green Blue)
• HSV (Hue Saturation Value)
• Indexed
• The other type of image we will frequently use is
  the binary image. This consists of two colours
  only black (0) and white (1).

9
Red Green Blue (RGB) model

• This can be thought of as a simple extension of
  the grey scale model where each pixel is composed
  of three colours red, green and blue each
  represented by a digital range of 0 to 255
  leading to 16,777,216 (16 million) colours.
• All available colours can be represented on the
  colour cube
• Instead of a single array of numbers we can now
  think of three array planes or for an m x n image
  an m x n x 3 array

10
Hue Saturation Value (HSV) model

• Whilst the RGB model is very simple it does not
  correspond very well with our intuitive
  understanding of colour. It is more natural to
  think in terms of
• Hue The colour starting with Red (0 degrees)
• Saturation The purity of the colour. A
  saturation of 1 is the pure colour and 0 is
  white.
• Value Is a measure of intensity with 0 as black
  and 1 as white.
• The combination of saturation value are often
  referred to as the tint of the colour.
• A simple transform will convert colour
  specification from RGB to HSV and vice versa
  (rgb2hsv, hsv2rgb)

11
Indexed colour maps

• Both RGB and HSV colour specifications are very
  memory intensive. For example a 768 x 1024 RGB
  image requires 2.36 Mbytes. Often double
  precision numbers are used in place of single
  byte values in which case the above image
  requires 9.44 Mbytes.
• An alternative is to use a small fixed range of
  colours (e.g. 256) and make the entries in the
  image array simply single byte pointers to the
  colour table.

Abstract from the image array
Abstract from the colour table
12
Machine vision

• Machine vision - giving robots sight
• Potentially the most powerful sensor is
  artificial vision
• Also called computer vision and machine vision.
• Machine vision is already used for both robotic
  non-robotic applications.
• Machine vision is a complex subject encompassing
  a number of different fields including optical
  engineering, analogue video processing, digital
  image processing, pattern recognition and
  artificial intelligence and computer graphics.
• The basic process is modelled on the mammalian
  eye/brain interaction.

13
Image processing stages

• Once an image has been captured we need to make
  some sense of it. Image processing involves three
  main actions
• image enhancement,
• image analysis
• image understanding.
• Image processing can be a complex and difficult
  operation and is still very much a research
  field.

14
Description of stages

• Image enhancement To remove unwanted artefacts
  such as noise, distortion, and non-uniform
  illumination from the image.
• Image analysis Converts the input image data
  into a description of the scene.
• Image understanding Classify each object and
  attempt to generate a logical decision based on
  the content of the image (e.g. the red object is
  at location x,y,z, or reject the component, or
  this is not a sheep, or there is an
  intruder").
• Examples of successful machine vision in
  industrial robotics
• Parts location
• Pick and place
• Parts recognition
• Parts inspection
• We will be more concerned in this module with
  image processing as applied to AI robotics
  (localisation and navigation).

15
Applications of machine vision
16
MatLab image formats 1

• MatLab uses the following main data
  representations for its image classes
• uint8 Unsigned 8-bit integers in the range 0
  to 255.
• uint16 Unsigned 16-bit integers in the range 0
  to 65,535.
• double Double precision numbers, by convention
  in the range 0 to 1 for images. Requires 4 bytes
  per pixel.
• logical values are 0 or 1, used in binary
  images.
• Only a very limited amount of data processing can
  be done with the UINT image classes. In fact with
  UINT16 you are virtually limited to displaying
  the image. Their function is to store images more
  efficiently on disk files. Almost all your work
  will be done with double precision images.

17
MatLab image formats 2

• Working with images almost always requires using
  double precision arithmetic. The following MatLab
  IPT functions convert between image classes and
  types
• im2uint8, im2uint16 convert input to uint8,
  uint16
• mat2gray converts any class double to double in
  range 0,1
• im2double converts data to double in range 0,1
• im2bw converts input to logical.
• Example
• h uint8(25 50 128 200)
• Performing the conversion g im2double(h)
  yields the result
• g
• 0.0980 0.1961
• 0.4706 0.7843

18
Loading displaying an images

• We can load an image with the imread function and
  display an image with the imshow function.
• imread
• A imread(filename, fmt)
• X,map imread(filename, fmt)
• In the first form the image is read into the
  array A and the format of the image fmt is
  optional.
• In the second form the image is read into the
  array X and the associated indexed map into map
  scaled 0 to 1 as double.
• imshow
• imshow(A)
• imshow(X,map)
• imshow has many other formats

19
Displaying the individual colours
function colourdisplay To demonstrate the
splitting of an image into its primary colours A
imread('monar.jpg') subplot(2,2,1)
imshow(A) title('RGB image') Redimage
A(,,1) subplot(2,2,2) imshow(Redimage) title(
'Red image') Greenimage A(,,2) subplot(2,2,3
) imshow(Greenimage) title('Green
image') Blueimage A(,,3) subplot(2,2,4)
imshow(Blueimage) title('Blue image')
20
Splitting an RGB image
21
Images types supported by MatLab

• The image processing toolbox supports four basic
  image types
• Indexed images
• Intensity images (MatLabs name for greyscale
  images)
• Binary images
• RGB full colour images
• MatLab allows easy conversion between image types
  using
• rgb2hsv to convert to a HSV image
• rgb2gray to convert to a grey scale image (note
  American spelling).
• rgb2ind to convert to an indexed image
• You should check the details in the MatLab help
  files.
• With the addition of the following line (and a
  variable name change) the previous example can be
  used to display the HSV components.
• B rgb2hsv(A)

22
HSV image components
23
Inspecting and recording image colours

• improfile which will reveal the colour intensity
  profile along a line defined on the image.
• Simply placing improfile on a line will allow you
  to interactively explore the colour profile
  alternatively using
• c improfile(I,xi,yi,n)
• will record in the array c the RGB values from
  image I with line segment end points defined by
  xi yi using n equally spaced points
•  pixval which will interactively record the
  location and colour components of each pixel as
  you move a cursor across the image.
•  impixel returns the RGB values for a specified
  pixel.

24
Example of using pixval
25
Example of using improfile
26
Tutorial

• Familiarise yourself with the machines log on,
  run Matlab, have a look at the Matlab Help
  information for the Image Processing Toolbox
  (IPT) and the Matlab demos.
• Re-create the M-files and Matlab code shown as
  part of this lecture.
• Load the image flower.jpg. Note what happens when
  you try and display it. Now re-size it by an
  appropriate amount and display it again. Save it
  to disk (flower2.jpg) and compare the size of the
  saved file with the original.
• Load the image bean.jpg. Look at the various
  colour channels and consider which channel would
  be most appropriate if you were about to create
  an image processing pipeline which could separate
  the beans from the background. Write an M-file to
  display the RGB image and each of its (R-, G-,
  B-) components, and the HSV image and each of its
  (H-, S-, V-) components. Repeat with flower.jpg.
• (From a previous assignment, in which students
  were asked to write a program to automatically
  count the numbers of large and small beans).