UNESCO module: Introduction to Computer Vision and Image Processing

1
UNESCO moduleIntroduction to Computer Vision
and Image Processing

• Department of Pattern Recognition and Knowledge
  Engineering
• Institute of Information Technology
• Hanoi, Vietnam
• Represented by LUONG CHI MAI
• lcmai_at_ioit.ncst.ac.vn

2
Outline of the presentation
Objectives, Prerequisite and Content

Brief Introduction to Lectures
Discussion and Conclusion

• This presentation summarizes the content and
  organization of lectures in module Image
  Processing and Computer Vision.

3
Objectives

• The course provides fundamental techniques of
  Image Processing and Computer Vision as well
  issues in practical use.

4
Prerequisite

• A basic background in mathematics and computers
  is necessary,
• Knowledge of the C programming language will
  enhance the usefulness of the algorithms used in
  programming,
• Understanding of signal and system theory is
  helpful in mastering transforms and compression.

5
Target audience

• Engineers, programmers, graphics specialists,
  multimedia developers, and imaging professionals
  will all appreciate Computer Vision and Image
  Processing's solid introduction
• Anyone who uses computer imaging.

6
Whats the Image Processing?

• Image Processing (IP) is used for two somewhat
  different purposes
• a. improving the visual appearance of images to a
  human view, and
• b. preparing images for measurement of the
  features and structures present.
• Image Processing Image ? Image
• 
  Transformation

7
Whats Computer Vision ?

• Computer Vision (CV) to create a model of the
  real word from images. A CV system recovers
  useful information about a scene from its
  two-dimensional projections. This recover
  requires the inversion of a many-to- one mapping.
  
• VisionGeometryMeasurementInterpretation

8
Relationships between subjects (1)
Many fields are related to Computer Vision Image
Processing (IP) techniques usually transform
images into other images, (enhancement,
correcting blurred, out-of-focus, compression ?
better 2D projection image for CV).The task of
information recovery is left to human
user. Computer Graphics (CG) generates images
from geometric primitives such as lines, circles,
and free-form surfaces. CV is the inverse
problem estimating the geometric primitives and
other features from images. CG Synthesis of
images. CV Analysis of images.

9
Relationships between subjects (2)
Pattern Recognition (PR) classifies numerical
and symbolic data. Techniques statistical and
syntactical. PR techniques play an important role
in CV for recognizing objects. Object recognition
in CV usually requires many other
techniques. Artificial Intelligence (AI) is
concerned with designing systems that are
intelligent and with studying computational
aspects of intelligent. CV is often considered as
a sub-field of AI Psyochophysics along with
cognitive science, studies human vision for a
long time. Many techniques in CV are related to
what is known abut human vision.
10
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

11
About the Chapters

• Chapters
• 1, 2, 3, 4, 5, 9, 10 related to Image Processing
  well known techniques to enhancement images.
• 6, 7, 8 related to Computer Visions

12
Image presentation (1)

• 1.1 Image capture, representation, and storage
• digital image, DPI, pixel...
• Example Variouse quantizing level (a) 6 bits
  (b) 4 bits (c) 2 bits (d) 1 bit.

13
Image presentation (2)

• 1.2 Color representation
• Color systems RGB, CMY/CMYK, HSI, YCbCr

14
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

15
Statistical operations (1)

• The algorithms are independent of the position of
  the pixels.
• Basic operation Histogram transformation

2.1 Gray-level transformation - Intensity
transformation - Look-up-table techniques - Gamma
correction function - Contrast streching
End-in-search 2.2 Histogram equalization
16
Statistical operations (2)

• 2.3 Multi-image operations
• Background substraction
• Multi-image averaging
• New-Pixel a Pixel1 (1 - a )Pixel2

17
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

18
Spatial operations and transformations (1)

• Combining the techniques and operations that deal
  with pixels and their neighbors (spatial
  operations).
• - Spatial filters (normally removing noise by
  reference to the neighboring pixel values),
• - Weighted averaging of pixel areas
  (convolutions),
• - Comparing areas on an image with known pixel
  area shapes so as to find shapes in images
  (correlation).
• - Edge detection and on detection of "interest
  point".

19
Spatial operations and transformations (2)

• Basic operation Templates and Convolution

I(x,y) - image T(i,j) - template of the size n x m
20
Spatial operations and transformations (3)

• 3.3 Other window operations
• Median filtering
• k-closest averaging
• Interest point
• Moravec operator
• Correlation

21
Spatial operations and transformations (4)

• 3.4 Two dimensional geometric transformations
• Frequently it is useful to zoom in on a part of
  an image, rotate, shift, skew or zoom out from an
  image.
• If (x,y) - the new coordinates and (x, y) -
  original coordinates
• Forward Transformation
• (x,y) f(x, y) for all (x, y) is created.
• Invest Transformation
• I(x, y) F(old image, x, y)

22
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

23
Segmentation and edge detection (1)

• Segmentation basic requirement for the
  identification and classification of objects in
  scene.
• Techniques splitting an image up into segments
  (also call regions or areas), each holds some
  property distinct from their neighbor.
• Approaches
• - identifying the edges (or lines) that run
  through an image
• - identifying regions (or areas) within an
  image.
• Region operations is the dual of edge operations.
  Ideally edge and region operations should give
  the same segmentation result, however, in
  practice the two rarely correspond.

24
Segmentation and edge detection (2)

• 4.1 Region operations
• Crudge edge detection
• Region merging
• Region spliting
• 4.2 Basic edge detection

25
Segmentation and edge detection (3)

• 4.3 First order derivative for edge detection
• Hc y_differ(x, y) value(x, y) value(x,
  y1)
• Hr X_differ(x, y) value(x, y) value(x-1,
  y)
• 4.3 Second-order edge detection
• 4.4 Pyramid edge detection
• 4.5 Crack edge detection
• 4.6 Edge following

26
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

27
Morphological and other area operations (1)

• Morphological defined
• - Morphology means the form and structure of an
  object, its related to shape
• - Digital morphology is a way to describe or
  analyze the shape of a digital object.

28
Morphological operations (2)

• 5.2 Basic morphological operations
• Binary dilation
• Binary erosion
• 5.3 Opening and closing operators
• Example The use of opening (a) An image having
  many connected objects, (b) Objects can be
  isolated by opening using the simple structuring
  element, (c) An image that has been subjected to
  noise, (d) The noisy image after opening showing
  that the black noise pixels have been removed.

29
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

30
Finding basic shapes (1)

• Previous chapters dealt with purely statistical
  and spatial operations.
• Techniques
• - looking at and processing whole images
• - uses information generated by the algorithms
  in the previous chapter.
• - finding basic two-dimensional shapes or
  elements of shapes by putting edges together to
  form lines that are likely represent real edges.

31
Finding basic shapes (2)

• 6.2 Hough transforms
• 6.3 Bresenhams algorithms
• 6.4 Using interest point
• 6.5 Labeling lines and regions

32
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

33
Reasoning, facts and inference (1)

• - Moving from the standard IP approach to CV to
  make statement about the geometry of objects and
  allocate labels to them.
• - Enhancing by making reasoned statements, by
  codifying facts, and making judgments based on
  past experience.
• - Introducing to some concepts in logical
  reasoning that relate specifically to CV.
• - Introducing training aspects of reasoning
  systems. The reasoning is the highest level of CV
  processing.

34
Reasoning, facts and inference (2)

• 7.1 Facts and Rules
• - Constructing a set of facts
• - Constructing a rule base.
• 7.2 Strategic learning
• Example A pedestal training and a pedestal
  description

35
Reasoning, facts and inference (3)

• 7.3 Networks and spatial descriptors
• Example Elementary network of spatial
  relationship
• L is all element of
• C is a subset of
• P with the visual property or
• R at this position with respect to
• 7.4 Rule orders

36
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

37
Pattern recognition and training (1)

• Previous chapter presented some methods used in
  reasoning about facts from image edges or
  textures, colours or surface positions.
• Some problems are better described as problems of
  determining a high level fact from a pattern of
  some kind. The term "pattern" has a wide range of
  meanings,
• We are particularly interested in sets of value
  that describe things, normally where the set of
  values is of a known size. This is different to
  looking at a scene of a flat surfaced object
  where we do not know how many corners there are,
  how many edges or how many surfaces.

38
Pattern recognition and training
(2)

• 8.1 General problem

39
Pattern recognition and training
(3)

• 8.2 Approaches to the decision making process
• 8.3 Decision functions
• 8.4 Determining decision functions
• 8.5 Non-linear decision functions
• 8.6 Using cluster means
• 8.7 Supervised and unsupervised learning
• - Statistical Bayesian likelihood supervised
  learning
• - Syntactical learning.

40
Pattern recognition and training (4)

• 8.4 Determining decision function
• - Searching for islands of simplicity,
• - Distance or similarity measure,

41
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

42
The frequency domain (1)

• Most signal processing is done in a mathematical
  space known as the frequency domain.
• In order to represent data in the frequency
  domain, some transform is necessary.
• The signal frequency of an image refers to the
  rate at which the pixel intensities change.
• - The high frequencies are concentrated around
  the axes dividing the image into quadrants.
• - The corners have lower frequencies. Low
  spatial frequencies are noted by large areas of
  nearly constant values.

43
The frequency domain (2)

• Fourier Transform of a spot (a) original
  image (b) Fourier Transform.
• 9.1 The Harley transform
• 9.2 The Fourier transform

44
Content of the course

• Chapter 1 Image presentation
• Chapter 2 Statistic operations
• Chapter 3 Spatial operations and transformations
• Chapter 4 Segmentation and edge detection
• Chapter 5 Morphological and other area area
  operations
• Chapter 6 Finding basic shapes
• Chapter 7 Reasoning, facts and inference
• Chapter 8 Pattern recognition and training
• Chapter 9 Frequency domain
• Chapter 10 Image compression

45
Image Compression (1)

• Compression of images problem of storing them
  in a form that systems need to get the following
  benefits
• - speedily operation (both compression and
  unpacking),
• - significant reduction in required memory, no
  significant loss of quality in the image,
• - format of output suitable for transfer or
  storage.
• Each of this depends on the user and the
  application.

46
Image Compression (2)

• A typical data compression system.

47
Image Compression (3)

• Run Length Encoding
• Huffman Coding
• Modified Huffman Coding
• Modified READ
• Arithmetic Coding
• LZW
• JPEG
• Other state-of-the-art image compression
  methods Fractal and Wavelet compression.

48
Conclusion

• Improvement
• Focus to recovering from 2D projection to create
  a object model
• - Coordinate system and camera calibration
• - Curve and surfaces
• - Dynamic vision
• Object recognition