CE 425 Image Analysis

and Machine Vision

Introduction

Md. Al-Amin Bhuiyan

Dept. of Computer Engineering
King Faisal University
Al Ahsa 31982, Saudi Arabia.
March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 1
 Course Overview
 Introduction  Geometric Operation
 Image Representation  Translation, Scaling, rotation, Affine
transformation, etc.
 Sampling, Quantization
 Image Enhancement  Image Transformations
 Fourier transform, Discrete cosine,
 File formats, Gray level mapping,
Hadamard, Harr transform
Histogram equalization,
Smoothing, Sharpening, etc.  Restoration
 Neighborhood Operations  Least square, Singular Value
Decomposition, etc.
 Convolution and correlation,
Linear filtering, etc.  Segmentation
 Region extraction, Thresholding,
 Edge Detection
Region growing, Region spliting, etc.
 Laplacian, Canny, Sobel, Prewitt,
LOG, etc.  Image Compression
 Lossy compression, Vector
quantisation, etc.

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 2

 Book References

 Digital Image Processing Using MATLAB by

Richard E. Woods and Steven L. Eddins, 2nd
Edition, Gatesmark Publishing, 2009. ISBN:
0982085400.
 Digital Image Processing by R. C. Gonzalez
and R. E. Woods, 2nd Edition, Prentice-Hall,
2002. ISBN: 013168728X.

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 3

 What are Images?
 Images are pictures: a way  Pictures are important to us
of recording and presenting because they can be an
information visually.
extraordinarily effective
 Computers process and medium for the storage and
stores numerical status of a communication of information.
scene.
 We use photography in
everyday life to create a
permanent record of our
visual experiences.
 In showing photograph, we
avoid the need for a lengthy,
tedious and ambiguous verbal
description of what was seen.

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 4

 Electromagnetic (EM) Spectrum
 Light is a particular type of electromagnetic radiation that can be seen and
sensed by the human eye. The visible band of EM spans the range 400-700 nm.
Shorter wavelength Longer wavelength
Gamma X-rays Ultra-violet Visible Spectrum Infra-red Radio waves
(10-3) (10-1) (101) (103) (109-13)

Blue Green Red

(436 nm) (546 nm) (7000 nm)

400 nm 500 nm 600 nm 700 nm

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 5
 Types of Images
• Infra-red Ultra-violet Radio-waves (radio astronomy)
• Visible light Micro-waves (radar) Roentgen (tomography)
• Sound-waves (echoscopy, sonar) Electrons (microscopy)
• Positron emission (PET-scan) Magnetic resonance (NMR)

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 6

 What is Image Processing?
 Analysis, manipulation, storage, and display of images
from sources such as photographs, drawings, and video.

 Image processing spans a sequence of three steps:

The input step (image capture and digitizing)
converts the differences in coloring and shading in
the picture into binary values that a computer can
process. The processing step can include image
enhancement and data compression. The output step
consists of the display or printing of the processed
image.
March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 7
 What is Image Processing?... …
Definition from the Webopedia:
Analyzing and manipulating images with a computer. Image
processing generally involves three steps:
[Link] an image with an optical scanner or directly through digital
photography.
2. Manipulate or analyze the image in some way. This stage can
include image enhancement and data compression, or the image may
be analyzed to find patterns that aren't visible by the human eye. For
example, meteorologists use image processing to analyze satellite
photographs.
3. Output the result. The result might be the image altered in some
way or it might be a report based on analysis of the image.

Image processing is the application of signal processing techniques to the

domain of images - two-dimensional signals such as photographs or video.

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 8

 Applications of Image Processing
1. Office automation: optical character recognition; document processing; logo
and icon recognition; identification of address on envelop; etc.
Industrial automation: automatic inspection of industrial parts; non-destructive
testing; automatic assembling; process related to VLSI manufacturing; PCB
checking; robotics; oil and natural gas exploration; seismography; process control
application; etc.
3. Bio-medical: ECG, EEG analysis; cytological, histological and stereological
applications; automated radiology and X-ray image analysis; mass-screening of
medical images such as chromosome slides for detection of various diseases,
mammograms, cancer smears; CAT, MRI, PET, and other tomographic images;
routine screening of samples; 3D scene reconstruction and analysis, etc.
4. Remote sensing: Tracking and surveying of natural resources; geographical
mapping, prediction and estimation of agricultural crops, hydrology, forestry,
mineralogy; estimation of urban growth, urban planning; environment and
pollution control; cartography, registration of satellite images with terrain maps;
monitoring traffic along roads, docks and airfields; food and fire control; etc.

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 9

 Applications of Image Processing
5. Scientific applications: high energy physics; bubble chamber and other forms of
track analysis; etc.
6. Criminology: Human face registration, detection and recognition, finger print
identification, dermetoglyphic analysis, forensic investigation; etc.
7. Astronomy and space application: restoration of images suffering from geometric
and photometric distortions; computing close-up picture of planetary surfaces; etc.
8. Meteorology: short-term weather forecasting, long –term climatic change
detection from satellite and other remote sensing data; cloud pattern analysis; etc.
9. Information technology: facsimile image transmission, video conferencing and
videophones; etc.
10. Entertainment and consumer electronics: HDTV; multimedia and video-editing;
etc.
11. Printing and graphic arts: color fidelity in desktop publishing; art conservation
and dissemination; etc.
12. Military applications: missile guidance and detection; target identification;
navigation of pilotless vehicles; reconnaissance; and range finding; etc.

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 10

 Image Representation
 The term image refers to a two-dimensional continuous light-intensity function,
denoted by i(x,y), where x and y represent spatial coordinates and the value or
amplitude of i at any point (x,y) gives the intensity (brightness) of the image at
that point.
 To be suitable for computer processing, an image function i(x,y) must be
discretized both spatially and in amplitude (brightness). Discretization of spatial
coordinates (x,y) is called image sampling and amplitude discretization is called
gray-level quantization.
column

Sample
f(x, y)
row
Quantize

y
x
March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 11
 Digital Images
 A continuous image i(x,y) is approximated by equally spaced
samples arranged in the form of an NM array as follows:
y
x
128 127 0 . . Gray
255 . . . .
  Level
120 . . . .
 f(x,y) 
 . . . . .
 . . . . .

 i(0,0) i(0,1) ... i(0, M 1) 

 

 i(1,0) i(1,1) ... i(1, M 1) 


'
 
i( x, y) 





 ' 


'
 
 
 

i( N 1,0) i( N 1,1) ... i( N 1, M 1)

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 12

 Color Images

R M B

W
Y C

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 13

 Color Simulation
B B
G G
R R
R+G+B R+G+B

B B
G G
R R
R+G+B R+G+B

B B
G G
R R
R+G+B R+G+B

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 14

 RGB Color Space

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 15

Fundamental Steps in Image Processing

Preprocessing Representation &

Segmentation
Description

Problem Image Knowledge Recognition &

Domain Acquisition
Base Interpretation

Result

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 16

 Digital Image Processing: in Details
Digital Image Processing

Digital Image Characteristics

Spatial Spectral

Gray-level Histogram DFT DCT

Pre-Processing

Enhancement Restoration

Point Processing Masking Filtering Degradation Models Inverse Filtering Wiener Filtering

Compression

Information Theory Lossless Lossy

LZW (gif) Transform-based (jpeg)

Segmentation

Edge Detection

Description

Shape Descriptors Texture Morphology

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 17

 Image Processing: in a Nut Shell
Image Preprocessing

Enhancement Restoration

• Inverse filtering
Spatial Spectral • Wiener filtering
Domain Domain

Filtering
Point Processing Spatial filtering • >>fft2/ifft2
• >>imadjust • >>filter2 • >>fftshift
• >>histeq

March 10, 2023 Dr. Al-Amin Bhuiyan mbhuiyan@[Link] 18