region labelling giving a region a name. image processing and computer vision: 62 introduction...
TRANSCRIPT
![Page 1: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/1.jpg)
Region labelling
Giving a region a name
![Page 2: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/2.jpg)
Image Processing and Computer Vision: 6 2
Introduction
Region detection isolated regions
Region description properties of regions
Region labelling identity of regions
![Page 3: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/3.jpg)
Image Processing and Computer Vision: 6 3
Contents
Template matching Rigid Non-rigid templates
Graphical methods Eigenimages Statistical matching Syntactical matching
![Page 4: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/4.jpg)
Image Processing and Computer Vision: 6 4
Template matching
Define a template a model of the object to be
recognised Define a measure of similarity
between template and similar sized image region
![Page 5: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/5.jpg)
Image Processing and Computer Vision: 6 5
Measure dissimilarity between image f[i,j] and template g[i,j]
Place template on image and compare corresponding intensities
Need a measure of dissimilarity
Last is best....
i, j Rmax f g f g
i, j R 2
f g i, j R
Similarity
![Page 6: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/6.jpg)
Image Processing and Computer Vision: 6 6
Expanding
If f and g fixed-fg a good measure of mismatch
fg a good measure of match
Compute match between template and image with cross-correlation
2
f g i, j R 2
f i, j R 2
g 2i , j R fg
i , j R
M i, j g k, l l n
ln
k m
km
f i k, j l
![Page 7: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/7.jpg)
Image Processing and Computer Vision: 6 7
g is constant, f varies and so influences MNormalisation
C is maximum where f and g are same.Limitations
number of templates required rotation and size changes partial views
C i, j g k, l
l n
ln
k m
k m
f i k, j l
2fl n
ln
k m
km
i k, j l
![Page 8: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/8.jpg)
Image Processing and Computer Vision: 6 8
0
20
40
60
80
100
1201
26
51
76
10
1
12
6
15
1
17
6
20
1
22
6
25
1
27
6
30
1
32
6
35
1
37
6
40
1
42
6
Position
No
n-N
orm
alis
ed
Co
rre
lati
on
Template
Input Output
![Page 9: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/9.jpg)
Image Processing and Computer Vision: 6 9
Flexible Templates
Shapes are seldom constant Variation
in shape itself in image of same shape viewpoint
Non-rigid representations capture variability
![Page 10: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/10.jpg)
Image Processing and Computer Vision: 6 10
Structure
Flexible image structures Linked by virtual springs
![Page 11: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/11.jpg)
Image Processing and Computer Vision: 6 11
Recognition Deform image structure
To equate model and image Move image structures
To colocate model and image Matching
externalexternalinternalinternal EWEWEtotal
![Page 12: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/12.jpg)
Image Processing and Computer Vision: 6 12
Learning the model Accuracy of model determines
success Model
For each control point average, variance of location
To be learnt with minimum external variation
size, orientation, inconsistency of location
![Page 13: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/13.jpg)
Image Processing and Computer Vision: 6 13
Parametric Models
Parametrically define the shape straight line, circle, parabola, …
Update parameters to match model and object
![Page 14: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/14.jpg)
Image Processing and Computer Vision: 6 14
Example – Face tracking
Eyes and mouth circles and parabolas locations, sizes, orientations
Templates define image structures
![Page 15: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/15.jpg)
Image Processing and Computer Vision: 6 15
Flexible templates, EigenImages
Attempt to capture intrinsic variability of data
Mathematical representation of variation
![Page 16: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/16.jpg)
Image Processing and Computer Vision: 6 16
Take samples from a population plot values of parameters on a
scatter diagram
Mathematical Foundation
![Page 17: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/17.jpg)
Image Processing and Computer Vision: 6 17
Rotate axes: one axis encodes most of information other axis encodes remainder
Generalise to multiple dimensions
![Page 18: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/18.jpg)
Image Processing and Computer Vision: 6 18
Images
Use outline co-ordinates image values
As the variables Normalise as much variability
![Page 19: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/19.jpg)
Image Processing and Computer Vision: 6 19
Hand Eigenimages
![Page 20: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/20.jpg)
Image Processing and Computer Vision: 6 20
Hand Gestures
![Page 21: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/21.jpg)
Image Processing and Computer Vision: 6 21
Range of Eigenimages
![Page 22: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/22.jpg)
Image Processing and Computer Vision: 6 22
Face Eigenimages
![Page 23: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/23.jpg)
Image Processing and Computer Vision: 6 23
Recognition
Retain n eigenvectors with largest eigenvalues
Form dot product of these with image data
Find nearest neighbour from training set
![Page 24: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/24.jpg)
Image Processing and Computer Vision: 6 24
Statistical Classification Methods
Derive characteristic feature measurements from image
Form a feature vector that identifies object as belonging to a predefined class
Need decision rules to make classification
![Page 25: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/25.jpg)
Image Processing and Computer Vision: 6 25
Linear Discriminant Analysis
Samples from different classes occupy different regions of feature space
Can define a line separating them
![Page 26: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/26.jpg)
Image Processing and Computer Vision: 6 26
Feature 1
Featu
re 2
Class A
Class B
![Page 27: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/27.jpg)
Image Processing and Computer Vision: 6 27
Decision
d(X) = F2 - mF1 - c
d(X) > 0 for points in class Ad(X) = 0 for points on lined(X) < 0 for points in class B
![Page 28: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/28.jpg)
Image Processing and Computer Vision: 6 28
height
weight
jockeys
basketball players?
jd 2
iu ijf i1
N
Rd minj1
N
jd
Nearest Neighbour Classifier
Assign the new sample to the population whose centroid is closest.
![Page 29: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/29.jpg)
Image Processing and Computer Vision: 6 29
Most Likely
Incorporate range of possible class values
2
2
xxCp
A
A
![Page 30: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/30.jpg)
Image Processing and Computer Vision: 6 30
Take population variation into account
Assume prior probability of observing class j is P(j)
e.g. 10% of population are jockeys
Assume a conditional probability distribution for each feature, x, of each population p(x|j).
height
weight
jockeys
basketball players?
Bayesian Classifiers
![Page 31: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/31.jpg)
Image Processing and Computer Vision: 6 31
P j | x p x|
j P j p x|
j P j j1
N
Multiply these curves by P(j) to give probability of a measurement belonging to each class.
Divide by total probability of measuring x, to normalise.
This gives the probability of the sample being from each class.
x
p
p(x|1)
p(x|2)
![Page 32: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/32.jpg)
Image Processing and Computer Vision: 6 32
Syntactic Recognition
Objects’ structure (outline) can be described linguistically Primitive shape elements = words Grammatically correct sentences = a
valid shape
![Page 33: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/33.jpg)
Image Processing and Computer Vision: 6 33
Shape Grammar A set of pattern primitives
terminal symbols A set of rules that define combinations
of primitives (sentences) the grammar
A start symbol represents a valid object
Non-terminal symbols represent substructures in the shape
![Page 34: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/34.jpg)
Image Processing and Computer Vision: 6 34
Recognition
Grammar is generative Recognition is degenerative
Recognition uses rules in reverse Terminal symbols are rewritten until a
valid start symbol is attained
![Page 35: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/35.jpg)
Image Processing and Computer Vision: 6 35
Chromosome Grammar
armpartright
armpartleft
armpartleft pair arm
partright armpair arm
sidepair armpair arm
pair armsidepair arm
pair armpair armchromosomesubmedian
c
c
![Page 36: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/36.jpg)
Image Processing and Computer Vision: 6 36
Chromosome Grammar
d
b
b
b
a
b
b
side
side
sideside
sideside
arm
armarm
armarm
![Page 37: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/37.jpg)
Image Processing and Computer Vision: 6 37
The Primitives
a b c d
a bc
b
ab
bb
b
b
b
a
ad
d
c
![Page 38: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/38.jpg)
Image Processing and Computer Vision: 6 38
Example
a bc
b
ab
bb
b
b
b
a
ad
d
c
![Page 39: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/39.jpg)
Image Processing and Computer Vision: 6 39
<submedian chromosome>
d b a b c b a b d b a b c b a b
<side><side> <arm><arm> <arm>c <arm>c
<side><side> <arm><arm> <arm>c <arm>cb b
<side><side> <arm> <right part><arm> <right part>
<side> <arm pair><side> <arm pair>
<arm pair><arm pair>
![Page 40: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/40.jpg)
Image Processing and Computer Vision: 6 40
Evaluation Classification rate Confusion matrix
![Page 41: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/41.jpg)
Image Processing and Computer Vision: 6 41
Classification Rate How often does the
classifier get the correct answer?
Selection of training and test data must be carefully done.
![Page 42: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/42.jpg)
Image Processing and Computer Vision: 6 42
Confusion matrix C(i,j) = number of times
pattern i was recognised as class j.
Want off-diagonal elements to be zero.
![Page 43: Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties](https://reader031.vdocuments.us/reader031/viewer/2022032105/56649d355503460f94a0c14b/html5/thumbnails/43.jpg)
Image Processing and Computer Vision: 6 43
Summary
Template matching Deformable templates Flexible templates Statistical classification