General Links
Computer Vision:
Pattern Recognition:
Specific Links
Introduction to Pattern Recognition
via Character Recognition
- Introduction to pattern
recognition (PostScript file)
- Transducers (digital
cameras and CCD
document scanners)
- Digital images (pixels,
bit depth and color)
- Lots more about imaging
and images
- Image
processing basics
- Stretching
and histogram equalization
- Optical
character recognition (brief introduction)
- Handwritten
address recognition demonstration
- Grids, connectivity and
contour tracing (PostScript file)
- M.I.T. reading machine for the blind
- What is hysteresis?
- Hysteresis smoothing (digital filtering)
Spatial Smoothing
- Regularization
- Logical smoothing
- Local
averaging
- Median
filtering
- Gaussian
smoothing
- Polygonal approximation
- Smoothing basics
(PostScript file)
- Function approximation
Spatial Differentiation
- Edge
detection and the Sobel operator
- Canny
edge-detector demo
- Mach
bands and lateral inhibition
- Limulus-the
horseshoe crab
- Sharpening, the Laplacian
and lateral inhibition in neural networks (PostScript file)
- Laplacian
edges
- Unsharp
masking
- More
edge detection
Spatial Moments
- Moments
of univariate distributions, skew and kurtosis (PostScript file)
- Basics on multivariate
moments (PostScript file)
- Moments of area & perimeter
- Moments for feature extraction
- Moments for pre-processing
- Moments as predictors of discrimination performance
Medial Axis Transformations
- Distance between sets
- Medial Axis (prairie-fire transformation)
- Skeletons (PostScript
file)
- Hilditch's algorithm
- Rosenfeld's algorithm
- Skeletonization
software
- Minkowski metrics
- Distance transforms
- Skeleton clean-up via distance transforms
- Medial axes via distance transforms
- Medial
axis transform
- Medial axis in
3D with applications
Topological Feature Extraction
- Convex hulls, concavities and enclosures
- Interactive
Java convex hull algorithms in 2D
- Clarkson's
code for 2D convex hulls
Processing Line Drawings
- Basics of Chain Coding
(PostScript file)
- Square, circular, and grid-intersect quantization
- Probability of obtaining diagonal elements
- Geometric probability
- Bertrand's
paradox (with Java applet simulations)
- Difference encoding & chain correlation functions
- Minkowski metric quantization
Detection of Structure in Noisy Pictures and
Dot Patterns
- Point-to-curve
transformations (Hough transform)
- Hough
Transform tutorial
- Line and circle detection
- Hypothesis testing approach
- Maximum-entropy quantization
- Hough
Transform demo on satellite photos
- Hough
Transform home page (and software)
- Hough
Transform publications
- More
Hough Transform code
- Interactive
histogram with Java applet
- Proximity graphs and perception
- Delaunay
Triangulations and Voronoi diagrams
- The shape of a set of points
- Relative neighbourhood graphs
- Sphere-of-influence graphs
- Alpha shapes
- Beta skeletons
Neural Networks and Bayesian Decision Theory
- Neural
Network Basics (FAQ's)
- Neural
Network Basics (with Java)
- Formal neurons, linear machines & perceptrons
- Introduction
to Probability and Statistics
- Basics
of Statistical Pattern Recognition
- Minimum risk classification
- Minimum error classification
- Discriminant functions (linear, quadratic, polynomial)
- The multivariate Gaussian probability density function
- Mahalanobis
distance classifiers
- Parametric decision rules
- Learning
from examples
Independence of Measurements, Redundancy, and
Synergism
- Independence in the discrete case
- Conditional and unconditional independence
- Dependence and correlation
- The best k measurements are not the k best
- Information theory and feature evaluation criteria
- Feature selection methods
- Models of spatial dependence between features
Neural Networks and Non-parametric Learning
- General
Learning Resources
- Perceptrons
- Non-parametric training of linear machines
- Error-correction procedures
- The fundamental learning theorem
- Multi-layer networks
- Reinforcement
Learning - An Intercative Tutorial
Estimation of Parameters and Classifier Performance
- Properties of estimators
- Dimensionality and sample size
- Estimation of the probability of misclassification
Nearest Neighbor Decision Rules
- The k-nearest neighbor rule
- Efficient search methods for nearest neighbors
- Decreasing space requirements
- Editing training sets
(compressed PostScript file)
- Error bounds
- Nearest
neighbor computation software
Using Contextual Information in Pattern Recognition
- Markov methods
- Forward dynamic programming and The Viterbi algorithm
- Combined bottom-up and top-down algorithms
Cluster Analysis and Unsupervised Learning
- Decision-directed learning (the
K-means algorithm)
- Graph-theoretic methods
- Agglomerative and divisive methods
- Clustering
software on the Web
Teaching Activities
Homepage