![[Go Back]](../IMAGES/next.gif){kind=small}
Chapter 1, Introduction
Chapter 2, The Digitized Image and its Properties
2.1 Basic Concepts
Image functions PE 2.A
The Dirac distribution and convolution
The Fourier transform
Images as a stochastic process
Images as linear systems
2.2 Image digitization
Sampling PE 2.B
Quantization
Color images
HW1B
2.3 Digital image properties
Metric and topological properties of
digital images
Histograms PE 2.C
Visual perception of the image
Image quality
Noise in images PE 2.D
Chapter 3, Data Structures for Image Analysis
3.1 Levels of image data representation
3.2 Traditional image data structures
Matrices
Chains
Topological data structures
Relational structures
3.3 Hierarchical data structures
Pyramids
Quadtrees
Chapter 4, Image Pre-processing
4.1 Pixel brightness transformations
Position-dependent brightness correction PE 4.A
Grey scale transformation PE 4.B
4.2 Geometric transformations
Pixel co-ordinate transformations PE 4.C
Brightness interpolation
4.3 Local pre-processing
Image Smoothing PE 4.D
PE 4.E
Edge detectors PE 4.F PE 4.G PE 4.H
Zero crossings of the second derivative PE 4.I
Scale in image processing
Canny edge detection PE 4.J
Edges in multispectral images
Other local pre-processing operators
Adaptive neighborhood pre-processing
4.4 Image restoration
Image restoration as inverse
convolution of the whole image
Degradations that are easy to restore PE 4.K
Inverse filtration PE 4.L PE 4.M
Wiener filtration
Chapter 5, Segmentation
5.1 Thresholding PE 5.A PE 5.B PE 5.C PE 5.D
Threshold detection methods PE 5.E
Multispectral thresholding
Thresholding in hierarchical data structures
5.2 Edge-based segmentation
Edge image thresholding
Edge relaxation
Border tracing
Edge following as graph searching
Edge following as dynamic programming
Hough transforms
Border detection using border location
information
Region construction from borders
5.3 Region growing segmentation
Region merging
Region splitting
Splitting and merging
5.4 Matching
Matching criteria
Control strategies of matching
5.5 Advanced optimal border and surface detection
approaches
Simultaneous detection of border
pairs
Optimal surface detection
Chapter 6, Shape Representation and Description
6.1 Region identification
6.2 Contour-based shape representation and description
Chain codes
Simple geometric shape representation
Fourier transforms of borders
Boundary description using segment sequences
B-spline representation
Other contour-based shape description approaches
Shape invariants
6.3 Region-based shape representation and description
Simple scalar region descriptors
Moments
Convex hull
Graph representation based on region skeleton
Region decomposition
Region neighborhood graphs
6.4 Shape classes
8.1 Image understanding control strategies
Parallel and serial processing control
Hierarchical control
Bottom-up control strategies
Model-based control strategies
Combined control strategies
Non-hierarchical control
8.2 Active contour models - snakes
8.3 Point distribution models
8.4 Pattern recognition methods in image understanding
Contextual image classification
8.5 Scene labeling and constraint propagation
Discrete relaxation
Probabilistic relaxation
Searching interpretation trees
8.6 Semantic image segmentation and understanding
Semantic region growing
Genetic image interpretation
8.7 Hidden Markov Models
Chapter 9, 3D Vision (Part I)
9.1 3D vision tasks
Marr's theory
Other vision paradigms: Active and purposive vision
9.2 Geometry for 3D vision
Basics of projective geometry
The single perspective camera
An overview of single camera calibration
Calibration of one camera from the known scene
Two cameras, stereopsis
The geometry of two cameras. The
fundamental matrix
Relative motion of the camera; the
essential matrix
Estimation of a fundamental matrix
from image point correspondences
Applications of the epipolar geometry in vision
Three and more cameras
Stereo correspondence algorithms
Active acquisition of range images
9.3 Radiometry and 3D vision
Grey level of a captured pixel from a
radiometric point of view
Surface reflectance
Shape from shading
Photometric stereo
11.1 Basic theory
11.2 The Fourier transform PE 11.A
11.3 Hadamard transform
11.4 Discrete cosine transform
11.5 Wavelets
11.6 Other discrete image transforms
11.7 Applications of discrete image transforms
PE 11.B PE 11.C
12.1 Image data properties
12.2 Discrete image transforms in image data
compression
12.3 Predictive compression methods
12.4 Vector quantization
12.5 Hierarchical and progressive compression
methods
12.6 Comparison of compression methods
12.7 Other techniques
12.8 Coding
12.9 JPEG and MPEG image compression PE 12.A
Chapter 13, Texture
13.1 Statistical texture description
Methods based on spatial frequencies
Co-occurrence matrices
Edge frequency
Primitive length (run length)
Laws' texture energy measures
Fractal texture description
Other statistical methods of texture description
13.2 Syntactic texture description
Shape chain grammars
Graph grammars
Primitive grouping in hierarchical textures
13.3 Hybrid texture description methods
13.4 Texture recognition method applications
Chapter 14, Motion Analysis
14.1 Differential motion analysis methods
14.2 Optical flow
Optical flow computation
Global and local optical flow estimation
Optical flow computation approaches
Optical flow in motion analysis
14.3 Motion analysis based on correspondence of interest
points
Detection of interest points
Correspondence of interest points
Object tracking
14.4 Kalman filters
Example
Last Modified: August 21, 2000