introduction to image processing

1. OE5
CS8009 Image Processing
Pritee Khanna
pkhanna@iiitdmj.ac.in
“One picture is worth more than ten thousand words”
Anonymous
January 2, 5, 2023

2. Overview
 Early days of computing, data was numerical
 Later, textual data became more common
 Today, many other forms of data: voice, music, speech,
images, computer graphics, etc.
 Each of these types of data are signals
 Loosely defined, a signal is a function that conveys
information

3. Signal Processing
 As long as people have tried to send or receive through
electronic media :
telegraphs, telephones, television, radar, etc.
there has been the realization that these signals may be
affected by the system used to acquire, transmit, or process
them
 Sometimes, these systems are imperfect and introduce
noise, distortion, or other artefacts
 Understanding the effects these systems have and finding
ways to correct them is the fundamental of signal
processing

4. Signal Processing and other fields
 Signals may be specific messages
 e.g., telegraph, telephone, television, digital networking, etc.
 We specifically introduce the information content into the signal
and hope to extract it later
 Man-made signals may be encoding of natural phenomena
 Audio signal, acquired image, etc.
 Signals may be created from scratch
 Speech generation, computer-generated music, computer
graphics, etc.
 Finally, we can sometimes merge these technologies
together by acquiring a natural signal, processing it, and then
transmitting it in some fashion

5.  From acquisition to interpretation, the initial signal may
be transformed, modified, and retransmitted numerous
times
Displayed to create
another signal
(visible light of the
display)
Recipient:
Decoded Decompressed
Transmitted codes of
image
Received
by eyes
Interpreted in some fashion by our brain
Sender:
Enhance
the picture
Compress for
transmission
Natural image Digital network
Displayed on
Computer
See a Scenario

6. Some Related Fields
 Digital Communication
 Computer Graphics
 Image Processing
 ComputerVision
 Pattern Recognition
 Robotics
 Artificial Intelligence
 Speech Synthesis and Recognition

7. To summarize…
Computer Vision, Image Processing, and
Computer Graphics often work together
to produce amazing results ……

8. What is a Digital Image? (1/4)
 A digital image is a representation of a two-
dimensional image as a finite set of digital values, called
picture elements or pixels

9. What is a Digital Image? (2/4)
 Pixel values typically represent gray levels, colors, heights,
opacities, etc.
 Remember digitization implies that a digital image is an
approximation of a real scene
1 pixel

10. What is a Digital Image? (3/4)
 Common image formats include:
 1 sample per point (B andW or Grayscale)
 3 samples per point (Red, Green, and Blue)
 4 samples per point (Red, Green, Blue, and “Alpha”)

11. What is a Digital Image? (4/4)
 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
 Where image processing ends and fields such as image
analysis and computer vision start ???

12. Image Processing
Applications

13. Image Enhancement
 One of the most common uses of DIP techniques:
improve quality, remove noise etc

14. Image Enhancement
Another Example: The Hubble Telescope
 Launched in 1990, the Hubble
telescope can take images of
very distant objects
 However, an incorrect mirror
made many of Hubble’s
images useless
 Image processing
techniques were
used to fix this

15. Object Recognition
a novel view recognized
reference view 1 reference view 2
Another application:
Inserting Artificial Objects into a Scene

16. Object Recognition Examples (1/2)
 Geographic Information Systems
 Digital image processing techniques are used extensively to
manipulate satellite imagery
 Terrain classification
 Meteorology

17. Object Recognition Examples (2/2)
 Night-Time Lights of the
World data set
 Global inventory of human
settlement
 Not hard to imagine the kind
of analysis that might be done
using this data
 Interpretation of aerial
photography is a problem
domain in both image
processing and computer vision

18. Character Recognition & Document
Handling

19. Face Detection, Recognition, and Tracking

20. Facial Expression Recognition

21. Security Applications
 Video Surveillance
 Biometrics

22. Fingerprint Verification / Identification

23. Medical Image Processing
Feature extraction and classification
with more than 95% accuracy
Mammogram Preprocessed
mammogram
Segmented
image
patches
Clustered
image
Preprocessing Segmentation
Feature Extraction
and
classification with
98% accuracy

24. Other Interesting Applications
 Target Recognition:
 Need of Defense organizations
 AutonomousVehicles:
 Land, Underwater, Space
 Traffic Monitoring
 Smart Human-Computer User Interfaces

25. Industrial Applications (1/3)
 Human operators are expensive, slow and unreliable
 Make machines do the job instead
 Industrial vision systems are used in all kinds of industries
 Can we trust them?

26. Industrial Applications (2/3)
 Quality assurance
 Can be used to control
 all parts of the product are on place (a)
 all places in pill pack are filled (b)
 The level of liquid in bottles (c)
 the quality of plastic details (d)
 and even control the corn flakes! (e)
(a) CD-ROM controller (b) Pack of pills (c) Level of liquid (d) Air-bladders
in plastic
(e) Corn flakes

27. Industrial Applications (3/3)
 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

28. 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

29. 41

30. Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

31. Key Stages in Digital Image Processing
Image Acquisition
– If output of the camera or sensor is not already in digital form, an
analog-to-digital converter digitizes it
– Frame grabber only needs circuits to digitize the electrical signal from
the imaging sensor to store the image in the memory of computer
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

32. Key Stages in Digital Image Processing
Image Enhancement
– To bring out obscured details, or simply to highlight certain features
of interest in an image
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

33. Key Stages in Digital Image Processing
Image Restoration
– Improving the appearance of an image
– Tend to be based on mathematical or probabilistic models of image
degradation
Distorted Image
Restored Image
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

34. Key Stages in Digital Image Processing
Morphological Processing
– Tools for extracting image components that are useful in the
representation and description of region shape, such as boundaries,
skeletons, and the convex hull
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

35. Image Enhancement
Image Restoration
To differentiate …..
Squares of
various size
Erosion
Operation
Dilation
Operation
Morphological Processing

36. Key Stages in Digital Image Processing
Segmentation
– To separate objects from the image background (one of the most
difficult task in DIP)
– Output is raw pixel data, constituting either the boundary or a region
or all the points in the region itself
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

37. Key Stages in Digital Image Processing
Object Recognition
– Recognition: the process that assigns a label to an object based on the
information provided by its descriptors
– Interpretation: assigning meaning to an ensemble objects
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
Image
Enhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression

38. – Make a decision whether the data should be represented as a
boundary or as a complete region
Boundary rep: Focus on external shape characteristics (corners, inflections)
Region rep: Focus on internal properties, such as texture or skeleton shape
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

39. 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
– Reducing the storage required to save an image or the bandwidth
required to transmit it
• Ex: JPEG (Joint Photographic Experts Group) image compression standard

40. 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

41. Text and Reference Books
 R. C. Gonzalez and R. E.Woods, Digital Image Processing,Third
Edition, Pearson, 2012.
 M Sonka,V Hlavac, and R Boyle, Image Processing,Analysis, and
MachineVision,Third Edition, Cengage learning, 2008.
 W. K. Pratt, Digital Image processing,Third Edition, John Wiley
& Sons Inc, 2001.

42. Grading Scheme
 Assignments and Quizzes: 15 marks
 Programming Quiz: 10
 Mid-Sem Exam: 20 marks
 End-Sem Exam: 40 marks
 Project: 15 marks
Teaching Assistant
Ms. Sudha Singh 22pcso03@iiitdmj.ac.in
Kindly see the details on the drive folder shared with you.

43. References: Thanks for images and text
 Digital Image Processing course by Dr. Brian Mac Namee
http://www.comp.dit.ie/bmacnamee/
 ComputerVision Home Page
http://www.cs.cmu.edu/afs/cs/project/cil/ftp/html/vision.html
 UNR ComputerVision Laboratory
http://www.cs.unr.edu/CVL
 Digital Image Processing course by Dr.Wanasanan Thongsongkrit
wanasana@eng.cmu.ac.th
 Google Image Search Engine
 R. C. Gonzalez and R. E.Woods, Digital Image Processing,Third
Edition, Pearson, 2012.