Академический Документы
Профессиональный Документы
Культура Документы
R.P.W. Duin
Pattern Recognition Group
Delft University of Technology
The Netherlands
prcourse@prtools.org
What is this? What occasion? Where are the faces? Who is who?
18 May 2008
18 May 2008
A
B
C
To which class
belongs an image
Which group?
18 May 2008
18 May 2008
Where is an object of
interest (detection);
What is it (classification)?
Fukunaga, K., Introduction to statistical pattern recognition, second edition, Academic Press, 1990.
Kohonen, T., Self-organizing maps, Springer Series in Information Sciences, Volume 30, Berlin, 1995.
Ripley, B.D., Pattern Recognition and Neural Networks, Cambridge University Press, 1996.
Devroye, L., Gyorfi, L., and Lugosi, G., A probabilistic theory of pattern recognition, Springer, 1996.
Schurmann, J. Pattern classification, a unified view of statistical and neural approaches, Wiley, 1996
Gose, E., Johnsonbaugh, R., and Jost, S., Pattern Recognition and Image Analysis, Prentice-Hall, 1996.
18 May 2008
License Plates
18 May 2008
18 May 2008
100 Objects
Is he in the database?
18 May 2008
18 May 2008
Yes!
10
18 May 2008
11
18 May 2008
12
3000
2500
2000
Flow cytometry
Earthquakes
1500
1000
500
18 May 2008
50
100
150
200
250
300
13
18 May 2008
14
A ? B
18 May 2008
15
Representation
18 May 2008
Sensor
Representation
Generalization
area
pixel_2
area
16
perimeter
Feature Representation
18 May 2008
Pixel Representation
perimeter
17
18 May 2008
pixel_1
18
Representation
Generalization
Representation
Sensor
D(x,xB1)
Classifier_2
B
A
B
Dissimilarity Representation
D(x,xA1)
19
Applications
size
Set of Examples
Representation
21
f(t)
t
Feature vector
area
Classification
error
Sensor
Test object
classified as A
Symbolic structures
A
F
E
Dissimilarities
Statistics needed to
solve class overlap
Representation
Generalization
Feature Space
Classification
x2
A -> A||B
B -> B1B2 B3..Bn
d(y,x2 )
x1
d(y,x1 )
Introduction to Statistical Pattern Recognition
22
perimeter
18 May 2008
Representation (Model)
Pattern Recognition
System
cost
(speed)
Physical Knowledge
complexity
(Attributed) graphs
20
18 May 2008
18 May 2008
Classifier_1
Combining Classifiers
18 May 2008
23
18 May 2008
24
p(A|x)
>
p(B|x)
A else B
p(x|A) p(A)
p(x)
>
p(x|B) p(B)
p(x)
A else B
A else B
p(x|A) p(A)
length
Bayes:
25
18 May 2008
p(length | male)
p(length | female)
18 May 2008
26
p(female) = 0.3
p(male) = 0.7
1.0
>
p(length | female) p(female) > p(length | male) p(male) female else male
length
Bayes:
18 May 2008
18 May 2008
28
Compactness
Representations of real world similar objects are close.
There is no ground for any generalization (induction) on representations
that do not obey this demand.
(A.G. Arkedev and E.M. Braverman, Computers and Pattern Recognition, 1966.)
18 May 2008
x2
A B
J F( A, B) = -------------------------2
2
A + B
(area)
(perimeter) x1
29
18 May 2008
30
x2
? to be classified as
B because it is most
close to an object A
area
(area)
area
x1
perimeter
31
18 May 2008
32
Density Estimation:
A
x2
(area)
color'
color
perimeter
(perimeter)
18 May 2008
B
?
?
perimeter
perimeter
(perimeter)
color
var(color)
perimeter
perimeter'=
var(perimeter)
color'=
18 May 2008
x1
33
18 May 2008
(perimeter)
x1
34
Multivariate Gaussians
0.5
Normal distribution =
Gaussian distribution
0.4
0.2
0.1
0 1-dimensional density:
-5
18 May 2008
Standard normal
distribution:
= 0, 2 = 1
0.3
1 ( x )2
p( x) =
exp
2
2
2
2
G=
3 1
1 2
k - dimensional density:
p( x) =
35
18 May 2008
1
2 k det(G )
1
exp ( x ) T G 1 ( x )
36
G= 1 0
0 1
p( x) =
G=
G= 1 0
0 3
37
18 May 2008
3 -1
-1 1
dP ( x) fraction of objects
=
volume
dx
38
18 May 2008
Parametric estimation
Assume Gaussian model
Estimate mean and covariance from data
Parametric estimation:
Assume a parameterized model, e.g. Gaussian
Estimate parameters from data
Resulting density is of the assumed form
1
n
G=
i =1
1
n 1
( x )
i =1
( xi )
1.5
0.5
-0.5
-1
39
18 May 2008
-1.5
-1.5
Nonparametric estimation
Histogram method:
1. Divide feature space in
N2 bins
2. Count the number of
objects in each bin
3. Normalize:
p ( x ) =
nij
18 May 2008
0.5
K (r ) > 0
K (r) dr = 1
For test object z sum all bins
p( z ) =
i , j =1
-0.5
1.5
2.5
Fix volume of bin, vary positions of bins, add contribution of each bin
Define bin-shape (kernel):
dy
ij
-1
n dxdy
40
18 May 2008
dx
1
z xi
K
hn i h
-1
-2
-3
-2
41
18 May 2008
-1
42
K ( x) =
1
h 2
exp
( )
2
x
2h2
Parzen:
p ( x )
x
18 May 2008
43
18 May 2008
44