Professional Documents
Culture Documents
Image Description: Shahram Ebadollahi
Image Description: Shahram Ebadollahi
Image Description: Shahram Ebadollahi
07)
Image Description
Shahram Ebadollahi
1 Motion (cont.)
1 Texture & Texture Quantification
1 Moments
1 Boundary Description
1 Color Description
1 MPEG-7 Descriptors
4/11/2007 2
Motion – object
Difference image:
d (i, j ) = 0 if | f1 (i, j ) − f 2 (i, j ) | ≤ ε object
motion
1 otherwise
n
d cum (i, j ) = ∑ ak | f1 (i, j ) − f k (i, j ) |
k =1 Cumulative difference image
4/11/2007 3
Motion Field
• A velocity vector is assigned to each pixel in the image
• Velocities due to relative motion between camera and the 3D
scene
• Image change due to motion during a time interval dt
• Velocity field that represents 3-dimensional motion of object
points across 2-dimensional image
Motion field
4/11/2007 4
Optical flow
• Motion of brightness patterns in image sequence
∂f ∂f ∂f
f ( x + dx, y + dy, t + dt ) = f ( x, y, t ) + dx + dy + dt + O(∂ 2 )
∂x ∂y ∂t
Gray-level difference at same
= f ( x, y, t ) + f x dx + f y dy + f t dt + O(∂ )
2 location over time is
equivalent to product of spatial
gray-level difference and
dx dy velocity
f ( x + dx, y + dy, t + dt ) = f ( x, y, t ) ⇒ − f t = f x + fy
dt dt
− f t = f x u + f y v = ∇f .c
dx dy
c=( , ) = (u, v)
dt dt
4/11/2007 known unknown 5
Optical Flow Constraints
− f t = f xu + f y v
Aperture problem
4/11/2007 6
Optical flow != Motion Field
MF ≠ 0 MF = 0
OF = 0 OF ≠ 0
4/11/2007 7
MPEG-7 Motion Descriptors
4/11/2007 9
Texture – Quantification Methods
4/11/2007 10
Statistical Texture Analysis
1st order statistics
image f → hf histogram
4/11/2007 12
Statistical Texture Analysis
2nd order statistics: Co-occurrence
f (m2 , n2 ) = j
d
θ P( d ,θ ) (i, j ) ≈ Pr[ f (m1 , n1 ) = i, f (m2 , n2 ) = j ]
f (m1 , n1 ) = i
1 2 j L
1 Joint gray-level histogram of pairs of 1
pixels 2
P( d ,θ ) ( i , j )
1 2D histogram
L
4/11/2007 13
Statistical Texture Analysis
2nd order statistics: Co-occurrence
P( d ,θ =0° ) (i, j ) =| {((k , l ), (m, n)) ∈ ( M × N ) × ( M × N ) :
k − m = 0, | l − n | = d , f (k , l ) = i, f (m, n) = j} |
P( d ,θ = 45° ) (i, j ) =| {((k , l ), (m, n)) ∈ ( M × N ) × ( M × N ) :
(k − m = d , l − n = −d ) ∨ (k = m = −d , l − n = d ), f (k , l ) = i, f (m, n) = j} |
P( d ,θ =90° ) (i, j )
90°
P( d ,θ =135° ) (i, j )
135° 45°
k
4/11/2007 15
Statistical Texture Analysis
2nd order statistics: Co-occurrence (statistics)
L L
i =1 j =1
(measure of image homogeneity)
L L
− ∑∑ P( d ,θ ) (i, j ) logP( d ,θ ) (i, j )
Entropy: i =1 j =1
L L
∑∑ λ κ
i − j P( d ,θ ) (i , j )
Contrast: i =1 j =1
(measure of local variations) L L
∑∑ [ijP
i =1 j =1
( d ,θ ) (i, j )] − µ x µ y
Correlation:
(measure of image linearity) σ xσ y
L L L L
4/11/2007 µ x = ∑ i ∑ P( d ,θ ) (i, j ) σ x = ∑ (i − µ x ) 2
∑P ( d ,θ ) (i, j ) 16
i =1 j =1 i =1 j =1
Statistical Texture Analysis
2nd order statistics: Difference Statistics
P( d ,θ ) (k ) = ∑P ( d ,θ )
i , j∈{1,1, L}
(i, j ) is a subset of co-occurrence matrix
|i − j | = k
L −1
k =0
L −1
Mean: ∑ kP
k =0
( d ,θ ) (k )
L −1
Entropy: − ∑ P( d ,θ ) (k ) log P( d ,θ ) (k )
k =0
L −1
Contrast: ∑ P(d ,θ ) (k )
k 2
k =0
4/11/2007 17
Statistical Texture Analysis
2nd order statistics: Fourier Power Spectrum
f ( x, y ) ↔ F (u , v)
v
π Indicator for size of
P ( r ) = 2∑ P ( r , θ ) dominant texture element
u or texture coarseness
θ =0
L/2
v
P(θ ) = ∑ P(r , θ )
Indicator for the
r =0
directionality of the texture
u
4/11/2007 18
Statistical Texture Analysis
2nd order statistics: Autocorrelation
M − pN −q
MN ∑ ∑ f ( k , l ) f ( k + p, l + q )
C ff ( p, q ) = k =1 l =1
( M − p )( N − q ) M N
∑∑
k =1 l =1
f 2 (k , l )
4/11/2007 19
MPEG-7 Texture Descriptors
image
1 Homogeneous texture
descriptors
1 Response of bank of
filters sensitive to image
scale and orientation
1 Non-homogeneous
texture descriptors • vertical
• horizontal
(edge histogram) • 45 degrees
1 Spatial distribution of • 135 degrees
edges • non-directional edge
4/11/2007 20
Structural Texture
4/11/2007 21
Structural Texture
4/11/2007 22
Geometric Moments
4/11/2007 23
Central Moments
Elliptical shape descriptors
µ pq = ∫ ∫ ( x − x0 ) ( y − y0 ) f ( x, y )dxdy
p q
µ11 covariance
θ
Principal moment of inertia: 2µ11
θ = 0.5 tan −1 ( )
( µ 20 + µ 02 ) + [( µ 20 − µ 02 ) 2 + 4µ112 ]1/ 2 µ 20 − µ 02
I1 =
2
a = 2( I1 / µ 00 )1/ 2 b = 2( I 2 / µ 00 )1/ 2
( µ 20 + µ 02 ) − [( µ 20 − µ 02 ) 2 + 4µ112 ]1/ 2
I2 =
2
( I1 + I 2 ) / m00
2
spreadness
4/11/2007
( I 2 − I1 ) /( I1 + I 2 ) elongation 24
Geometric Moment Invariants
x' a11 a12 x
( x, y ) ( x' , y' ) y ' = a a22 y
21
Scale
4/11/2007 25
Boundary Representation –
Chain Codes
4/11/2007 26
Color descriptors
Color histogram
4/11/2007 27
Which descriptors?
Image Feature Evaluation
1. Prototype Performance
1 Classify (Segment) image using
different features
1 Evaluate which feature is optimal
(minimum classification error)
2. Figure of Merit
1 Establish functional distance
measurements between set of
image features (large distance 2
low classification error)
1 Bhattacharyya distance
4/11/2007 28