PR01
PR01
PR01
Text Books
• Pattern Recognition
• S. Theodoridis & K. Koutrumbas
• Pattern Classification
• R. Duda et al.
• R. Shalkoff
Pattern Recognition:
What is it?
The act of taking as input sensed
data(measurements)
and taking an action
based on the “category” or “class”
ofthe pattern.
What It Does
• Build a machine that can recognize patterns:
x1 ,..., xl ,
Sea bass
Species
Salmon
• Problem Analysis
• Length
• Lightness
• Width
• Number and shape of fins
• Position of the mouth, etc…
• Preprocessing
– isolate fishes from one another and from the
background
• Feature Extraction
– send isolated fish image to feature extractor
– it reduces the data too
• Classification
– pass the features to a classifier
• Classification
Lightness Width
• adding correlated feature does not improve
anything and is thus redundant
Issue of generalization!
A compromise between training and testing
Pattern Recognition Systems
• Sensing
• Classification
– Use a feature vector provided by a feature extractor to assign
the object to a category
• Post Processing
– error rate
– risk
– use context
The Design Cycle
• Data collection
• Feature Choice
• Model Choice
• Training
• Evaluation
• Computational Complexity
• Data Collection
• Unsupervised learning
x2
Unsupervised Learning
x1
x2
Unsupervised Learning
x1
x2