fetch.php
DESCRIPTION
fetch.phpTRANSCRIPT
-
118 May 2008 1Introduction to Statistical Pattern Recognition
Introduction to Statistical Pattern Recognition
R.P.W. Duin
Pattern Recognition GroupDelft University of Technology
The Netherlands
18 May 2008 2Introduction to Statistical Pattern Recognition
Pattern Recognition Problem
What is this? What occasion? Where are the faces? Who is who?
18 May 2008 3Introduction to Statistical Pattern Recognition
Pattern Recognition Problems
Which group?
A
B
C
18 May 2008 4Introduction to Statistical Pattern Recognition
Pattern Recognition Problems
To which classbelongs an image
To which class (segment)belongs every pixel?
Where is an object ofinterest (detection);
What is it (classification)?
18 May 2008 5Introduction to Statistical Pattern Recognition
Pattern Recognition BooksFukunaga, 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.
Vapnik, V.N., Statistical Learning Theory, Wiley, New York, 1998.
Duda, R.O., Hart, P.E., and Stork, D.G. Pattern Classification, 2d Edition Wiley, New York, 2001.
Hastie, T., Tibishirani, R., Friedman, J., The Elements of Statistical Learning, Springer, Berlin, 2001.
Webb, A. Statistical Pattern Recognition Wiley, 2002.
F. van der Heiden, R.P.W. Duin, D. de Ridder, and D.M.J. Tax, Classification, Parameter Estimation, State Estimation: An Engineering Approach Using MatLab, Wiley, New York, 2004, 1-440.
Bishop, C.M., Pattern Recognition and Machine Learning, Springer 2006
Theodoridis, S. and Koutroumbas, K. Pattern Recognition, 4th ed., Academic Press, New York, 2008.
Statsoft, Electronic Textbook, http://www.statsoft.com/textbook/stathome.html18 May 2008 6Introduction to Statistical Pattern Recognition
Pattern Recognition: OCR
Kurzweil Reading Edge
Automatic text reading machine with speech synthesizer
-
218 May 2008 7Introduction to Statistical Pattern Recognition
Pattern Recognition: Traffic
Road sign detectionRoad sign recognition
18 May 2008 8Introduction to Statistical Pattern Recognition
Pattern Recognition: Traffic
License Plates
18 May 2008 9Introduction to Statistical Pattern Recognition
Pattern Recognition: Images
100 Objects
18 May 2008 10Introduction to Statistical Pattern Recognition
Pattern Recognition: Faces
Is he in the database? Yes!
18 May 2008 11Introduction to Statistical Pattern Recognition
Pattern Recognition: Speech
18 May 2008 12Introduction to Statistical Pattern Recognition
Pattern Recognition: Pathology
MRI Brain Image
-
318 May 2008 13Introduction to Statistical Pattern Recognition
Pattern Recognition: Pathology
0 50 100 150 200 250 3000
500
1000
1500
2000
2500
3000
Flow cytometry
18 May 2008 14Introduction to Statistical Pattern Recognition
Pattern Recognition: Seismics
Earthquakes
18 May 2008 15Introduction to Statistical Pattern Recognition
Pattern Recognition: Shape Recognition
Pattern Recognition is very often Shape Recognition: Images: B/W, grey value, color, 2D, 3D, 4D Time Signals Spectra
18 May 2008 16Introduction to Statistical Pattern Recognition
Pattern Recognition: Shapes
Examples of objects for different classes
Object of unknown class to be classified
A B?
18 May 2008 17Introduction to Statistical Pattern Recognition
Pattern Recognition System
Representation GeneralizationSensor
B
A
B
A
perimeter
area
perimeter
area
Feature Representation
18 May 2008 18Introduction to Statistical Pattern Recognition
Pattern Recognition System
Representation GeneralizationSensor
B
A
B
A
pixel_1
pixe
l_2
Pixel Representation
-
418 May 2008 19Introduction to Statistical Pattern Recognition
Pattern Recognition System
Representation GeneralizationSensor
B
A
B
A
D(x,xA1)
D(x
,xB
1)
Dissimilarity Representation
18 May 2008 20Introduction to Statistical Pattern Recognition
Pattern Recognition System
Representation GeneralizationSensor
B
A
B
A
Classifier_1
B
A
B
A
B
A
B
A
Combining Classifiers
Clas
sifie
r_2
18 May 2008 21Introduction to Statistical Pattern Recognition
Applications
Biomedical: EEG, ECG, Rntgen, Nuclear, Tomography, Tissues, Cells, Chromosomes, Bio-informatics
Speech Recognition, Speaker Identification. Character Recognition Signature Verification Remote Sensing, Meteorology Industrial Inspection Robot Vision Digital Microscopy
Notes: not always, but very often image basedno strong models available
18 May 2008 22Introduction to Statistical Pattern Recognition
Requirements and GoalsSet of Examples Physical Knowledge
Representation Representation (Model)
Classification
size
complexity
cost(speed)
error
Minimize desired set of examplesMinimize amount of explicit knowledgeMinimize complexity of representationMinimize cost of recognitionMinimize probability of classification error
Pattern RecognitionSystem
18 May 2008 23Introduction to Statistical Pattern Recognition
Possible Object RepresentationsMeasurement samples
Feature vector
Sets of segments or primitives
Outline samples (shape)
Symbolic structures
(Attributed) graphs
Dissimilarities
Atf(t)
A -> A||BB -> B1B2B3..BnA B
C DE
F
area
perimeter
d(y,x2)
d(y,x1)
18 May 2008 24Introduction to Statistical Pattern Recognition
Pattern Recognition System
Statistics needed to solve class overlap
Test object classified as A
Representation GeneralizationSensor
Classification Feature Space
1x
2xBBA
-
518 May 2008 25Introduction to Statistical Pattern Recognition
Bayes decision rule, formal
p(A|x) > p(B|x) A else B
p(x|A) p(A) > p(x|B) p(B) A else B
Bayes: p(x|A) p(A) p(x|B) p(B) p(x) p(x)>
A else B
2-class problems: S(x) = p(x|A) p(A) - p(x|B) p(B) > 0 A else B
n-class problems: Class(x) = argmax(p(x|) p())
18 May 2008 26Introduction to Statistical Pattern Recognition
Decisions based on densities
length
p(length | male)p(length | female)
What is the gender of somebody with this length?
p(female | length) = p(length | female) p(female) / p(length)p(male | length) = p(length | male) p(male) / p(length)Bayes: {
18 May 2008 27Introduction to Statistical Pattern Recognition
Decisions based on densities
length
p(length | male) p(male)p(length | female) p(female)
What is the gender of somebody with this length?
p(female | length) = p(length | female) p(female) / p(length)p(male | length) = p(length | male) p(male) / p(length)Bayes: {
p(female) = 0.3p(male) = 0.7
1.0
18 May 2008 28Introduction to Statistical Pattern Recognition
Bayes decision rule
p(female | length) > p(male | length) female else maleBayes:
p(length | female) p(female) p(length | male) p(male) p(length) p(length)>
p(length | female) p(female) > p(length | male) p(male) female else male
pdf estimated from training set class prior probabilitiesknown, guessed or estimated
18 May 2008 29Introduction to Statistical Pattern Recognition
What are Good Features?
x
A B
Good features are discriminative.
Good features are have to be defined by experts
Sometimes to be found by statistics
e.g. Fisher Criterion:
JF A B,( )A B 2
A2 B2+--------------------------=A B
18 May 2008 30Introduction to Statistical Pattern Recognition
Compactness
The compactness hypothesis is notsufficient for perfect classificationas dissimilar objects may be close. class overlap probabilities
Representations of real world similar objects are close. There is no ground for any generalization (induction) on representationsthat do not obey this demand.
(A.G. Arkedev and E.M. Braverman, Computers and Pattern Recognition, 1966.)
1x
2x
(perimeter)
(area)
-
618 May 2008 31Introduction to Statistical Pattern Recognition
Distances and Densities
? to be classified as
B because it is mostclose to an object A
A because the localdensity of B is larger.
1x
2x
(perimeter)
(area)
A
B?
18 May 2008 32Introduction to Statistical Pattern Recognition
Distances: Scaling Problem
Before scaling: D(X,A) < D(X,B) After scaling: D(X,A) > D(X,B)
perimeter
area
X B
Aarea
perimeter
X B
A
18 May 2008 33Introduction to Statistical Pattern Recognition
How to Scale in Case of no Natural Features
Make variances equal:
color
perimeter
color'
)colorvar(colorcolor'=
)perimetervar(perimeterperimeter'=
perimeter
18 May 2008 34Introduction to Statistical Pattern Recognition
Density Estimation:
What is the probability of finding an objectof class A (B) on this place in the 2D space?
What is the probability of finding an objectof class A (B) on this place in the 1D space?
1x(perimeter)
(area)
A
B?
2x
(perimeter) 1x?
18 May 2008 35Introduction to Statistical Pattern Recognition
The Gaussian distribution (3)
1-dimensional density:
= 2
2
2
)(21exp
21)(
xxp
Normal distribution =Gaussian distribution
Standard normaldistribution: = 0, 2 = 1
95% of data between[ - 2, + 2 ] (in 1D!)
-5 0 50
0.1
0.2
0.3
0.4
0.5
18 May 2008 36Introduction to Statistical Pattern Recognition
Multivariate Gaussians
k - dimensional density:
= )()(
21exp
)det(21)( 1T xGx
Gxp
k
G G == 3 13 1
1 21 2
-
718 May 2008 37Introduction to Statistical Pattern Recognition
Multivariate Gaussians (2)
G == 1 01 00 10 1
G == 3 03 00 10 1
G == 3 3 --11--11 11
G == 1 01 00 30 3
18 May 2008 38Introduction to Statistical Pattern Recognition
Density estimation (1)
The density is defined on the whole feature space. Around object x, the density is defined as:
Given n measured objects, e.g. persons height (m) how can we estimate p(x)?
==volume
objectsoffraction)()(dxxdPxp
18 May 2008 39Introduction to Statistical Pattern Recognition
Density estimation (2)
Parametric estimation: Assume a parameterized model, e.g. Gaussian Estimate parameters from data Resulting density is of the assumed form
Non parametric estimation: Assume no formal structure/model, choose approach Estimate density with chosen approach Resulting density has no formal form
18 May 2008 40Introduction to Statistical Pattern Recognition
Parametric estimation
Assume Gaussian model Estimate mean and covariance from data
-1.5 -1 -0.5 0 0.5 1 1.5 2 2.5-1.5
-1
-0.5
0
0.5
1
1.5
2
=
=n
iin x
1
1 )()( T1
11 xxG i
n
iin =
=
18 May 2008 41Introduction to Statistical Pattern Recognition
Nonparametric estimation
Histogram method:1. Divide feature space in
N2 bins2. Count the number of
objects in each bin3. Normalize:
, 1
( ) ijNij
i j
np x
n dxdy=
=
x
y
dx
dy
18 May 2008 42Introduction to Statistical Pattern Recognition
Parzen density estimation (1)
Fix volume of bin, vary positions of bins, add contribution of each binDefine bin-shape (kernel):
For test object z sum all bins
-2 -1 0 1 2 3 4 5 6 7-3
-2
-1
0
1
2
3
40)( >rK
= ii
hK
hnp xzz 1)(
1)( = rr dK
-
818 May 2008 43Introduction to Statistical Pattern Recognition
Parzen density estimation (2)
)(xp
x
Parzen:
With Gaussian kernel: ( )22221 exp)( hxhxK =
18 May 2008 44Introduction to Statistical Pattern Recognition
Parametric vs. Nonparametric
Parametric estimation, based on some model: Model parameters to estimate More samples required than parameters Model assumption could be incorrect resulting in
erroneous conclusions Non parametric estimation, hangs on data directly:
Assume no formal structure/model Almost no parameters to estimate Erroneous estimates are less likely