Pattern Recognition Concepts

Chapter 4: Shapiro and Stockman How should objects be represented? Algorithms for recognition/matching * nearest neighbors * decision tree * decision functions * artificial neural networks How should learning/training be done?
CSE803 Fall 2012 1

Feature Vector Representation

X=[x1, x2, , xn], each xj a real number Xj may be object measurement Xj may be count of object parts Example: object rep. [#holes, Area, moments, ]

CSE803 Fall 2012

Possible features for char rec.

CSE803 Fall 2012

Some Terminology

Classes: set of m known classes of objects (a) might have known description for each (b) might have set of samples for each Reject Class: a generic class for objects not in any of the designated known classes Classifier: Assigns object to a class based on features
CSE803 Fall 2012 4

Classification paradigms

CSE803 Fall 2012

Discriminant functions

Functions f(x, K) perform some computation on feature vector x Knowledge K from training or programming is used Final stage determines class CSE803 Fall 2012 6

Decision-Tree Classifier

Uses subsets of features in seq. Feature extraction may be interleaved with classification decisions Can be easy to design and efficient in execution

CSE803 Fall 2012

Decision Trees
#holes 0 1 moment of inertia <t best axis direction
0 60 90

2 #strokes

#strokes

t 0 #strokes 2
x 4

w 0 A CSE803 Fall 2012

8 8

Classification using nearest class mean

Compute the Euclidean distance between feature vector X and the mean of each class. Choose closest class, if close enough (reject otherwise) Low error rate at left

CSE803 Fall 2012

Nearest mean might yield poor results with complex structure

Class 2 has two modes If modes are detected, two subclass mean vectors can be used

CSE803 Fall 2012

10

Scaling coordinates by std dev

CSE803 Fall 2012

11

Another problem for nearest mean classification

If unscaled, object X is equidistant from each class mean With scaling X closer to left distribution Coordinate axes not natural for this data 1D discrimination possible with PCA

CSE803 Fall 2012

12

Receiver Operating Curve ROC

Plots correct detection rate versus false alarm rate Generally, false alarms go up with attempts to detect higher percentages of known objects

CSE803 Fall 2012

13

Confusion matrix shows empirical performance

CSE803 Fall 2012

14

Bayesian decision-making

CSE803 Fall 2012

15

Normal distribution

0 mean and unit std deviation Table enables us to fit histograms and represent them simply New observation of variable x can then be translated into probability
CSE803 Fall 2012 16

Cherry with bruise

Intensities at about 750 nanometers wavelength Some overlap caused by cherry surface turning away

CSE803 Fall 2012

17

Parametric Models can be used

CSE803 Fall 2012

18