Title: Active Shape Models: Their Training and Applications Cootes, Taylor, et al.
1Active Shape ModelsTheir Training and
ApplicationsCootes, Taylor, et al.
- Robert Tamburo
- July 6, 2000
- Prelim Presentation
2Other Deformable Models
- Hand Crafted Models
- Articulated Models
- Active Contour Models Snakes
- Fourier Series Shape Models
- Statistical Models of Shape
- Finite Element Models
3Motivation Prior Models
- Lack of practicality
- Lack of specificity
- Lack of generality
- Nonspecific class deformation
- Local shape constraints
4Goals of Active Shape Model (ASM)
- Automated
- Searches images for represented structures
- Classify shapes
- Specific to ranges of variation
- Robust (noisy, cluttered, and occluded image)
- Deform to characteristics of the class
represented - Learn specific patterns of variability from a
training set
5Goals of ASM (contd.)
- Utilize iterative refinement algorithm
- Apply global shape constraints
- Uncorrelated shape parameters
- Better test for dependence?
6Point Distribution Model (PDM)
- Captures variability of training set by
calculating mean shape and main modes of
variation - Each mode changes the shape by moving landmarks
along straight lines through mean positions - New shapes created by modifying mean shape with
weighted sums of modes
7PDM Construction
8Labeling the Training Set
- Represent example shapes by points
- Point correspondence between shapes
9Aligning the Training Set
- xi is a vector of n points describing the the ith
shape in the set - xi(xi0, yi0, xi1, yi1,, xik,
yik,,xin-1, yin-1)T - Minimize
- Ej (xi M(sj, ?j)xk tj)TW(xi
M(sj, ?j)xk tj) - Weight matrix used
-
10Alignment Algorithm
- Align each shape to first shape by rotation,
scaling, and translation - Repeat
- Calculate the mean shape
- Normalize the orientation, scale, and origin of
the current mean to suitable defaults - Realign every shape with the current mean
- Until the process converges
11Mean Normalization
- Ensures 4N constraints on 4N variables
- Equations have unique solutions
- Guarantees convergence
- Independent of initial shape aligned to
- Iterative method vs. direct solution
12Aligned Shape Statistics
- PDM models cloud variation in 2n space
- Assumptions
- Points lie within Allowable Shape Domain
- Cloud is hyper-ellipsoid (2n-D)
13Statistics (contd.)
- Center of hyper-ellipsoid is mean shape
- Axes are found using PCA
- Each axis yields a mode of variation
- Defined as , the eigenvectors of covariance
matrix - , such that
- ,where is the kth eigenvalue of S
14Approximation of 2n-D Ellipsoid
- Most variation described by t-modes
- Choose t such that a small number of modes
accounts for most of the total variance
and the
approximated variance , then
15Generating New Example Shapes
- Shapes of training set approximated by
- , where is the matrix
of the first t eigenvectors and
is a vector of weights - Vary bk within suitable limits for similar shapes
16Application of PDMs
- Applied to
- Resistors
- Heart
- Hand
- Worm model
17Resistor Example
- 32 points
- 3 parameters capture variability
18Resistor Example (cont.d)
- Lacks structure
- Independence of parameters b1 and b2
- Will generate legal shapes
19Resistor Example (cont.d)
20Resistor Example (cont.d)
21Resistor Example (cont.d)
22Heart Example
- 66 examples
- 96 points
- Left ventricle
- Right ventricle
- Left atrium
- Traced by cardiologists
23Heart Example (cont.d)
24Heart Example (cont.d)
25Hand Example
- 18 shapes
- 72 points
- 12 landmarks at fingertips and joints
26Hand Example (cont.d)
- 96 of variability due to first 6 modes
- First 3 modes
- Vary finger movements
27Worm Example
- 84 shapes
- Fixed width
- Varying curvature and length
28Worm Example (cont.d)
- Represented by 12 point
- Breakdown of PDM
29Worm Example (cont.d)
- Curved cloud
- Mean shape
- Varying width
- Improper length
30Worm Example (cont.d)
- Linearly independent
- Nonlinear dependence
31Worm Example
- Effects of varying first 3 parameters
- 1st mode is linear approximation to curvature
- 2nd mode is correction to poor linear
approximation - 3rd approximates 2nd order bending
32PDM Improvements
- Automated labeling
- 3D PDMs
- Nonlinear PDM
- Polynomial Regression PDMs
- Multi-layered PDMs
- Hybrid PDMs
- Chord Length Distribution Model
- Approximation problem
33PDMs to Search an Image - ASMs
- Estimate initial position of model
- Displace points of model to better fit data
- Adjust model parameters
- Apply global constraints to keep model legal
34Adjusting Model Points
- Along normal to model boundary proportional to
edge strength
35Calculating Changes in Parameters
- Initial position
- Move X as close to new position (X dX)
- Calculate dx to move X to dX
- Update parameters to better fit image
- Not usually consistent with model constraints
- Residual adjustments made by deformation
36Model Parameter Space
- Transforms dx to parameter space giving allowable
changes in parameters, db - Recall
- Find db such that
- - yields
- Update model parameters within limits
37Applications
- Medical
- Industrial
- Surveillance
- Biometrics
38ASM Application to Resistor
- 64 points (32 type III)
- Adjustments made finding strongest edge
- Profile 20 pixels long
- 5 degrees of freedom
- 30, 60, 90, 120 iterations
39ASM Application to Heart
- Echocardiogram
- 96 points
- 12 degrees of freedom
- Adjustments made finding strongest edge
- Profile 40 pixels long
- Infers missing data (top of ventricle)
40ASM Application to Hand
- 72 points
- Clutter and occlusions
- 8 degrees of freedom
- Adjustments made finding strongest edge
- Profile 35 pixels long
- 100, 200, 350 iterations
41Conclusions
- Sensitivity to orientation of object in image to
model - Sensitivity to large changes in scale?
- Sensitive to outliers (reject or accept)
- Sensitivity to occlusion
- Quantitative measures of fit
- Overtraining
- Occlusion, cluttering, and noise
- Dependent on boundary strength
- Real time
- Extension to 3rd dimension
- Gray level PDM
42MR of Brain2
- Improves ASM
- Tests several model hypotheses
- Outlier detection adjustment/removal
- 114 landmark points
- 8 training images
- Model structures of brain together
- Model brain structures
43MR Brain (cont.d)
44MR Brain (cont.d)
Separate
Together
45MR Brain (cont.d)
46(No Transcript)
47Thank You For
Your Time!
THE END
48References
- 1 Cootes, Taylor, et al., Active Shape Models
Their Training and Application. Computer Vision
and Image Understanding, V16, N1, January, pp.
38-59, 1995 - 2 - Duta and Sonka, Segmentation and
Interpretation of MR Brain Images An Improved
Active Shape Model. IEEE Transactions on Medical
Imaging, V17, N6, December 1998
49Hand Crafted Models
- Built from subcomponents (circles, lines, arcs)
- Some degree of freedom
- May change scale, orientation, size, and position
- Lacks generality
- Detailed knowledge of expected shapes
- Application specific
back
50Articulated Models
- Built from rigid components connected by sliding
or rotating joints - Uses generalized Hough transform
- Limited to a restricted class of variable shapes
back
51Active Contours Snakes
- Energy minimizing spline curves
- Attracted toward lines and edges
- Constraints on stiffness and elastic parameters
ensure smoothness and limit degree to which they
can bend - Fit using image evidence and applying force to
the model and minimize energy function - Uses only local information
- Vulnerable to initial position and noise
back
52Spline Curves
- Splines are piecewise polynomial functions of
order d - Sum of basis functions with applied weights
- Spans joined by knots
back
53Fourier Series Shape Models
- Models formed from Fourier series
- Fit by minimizing energy function (parameters)
- Contains no prior information
- Not suitable for describing general shapes
- Finite number of terms approximates a square
corner - Relationship between variations in shape and
parameters is not straightforward
back
54Statistical Models of Shape
- Register landmark points in N-space to
estimate - Mean shape
- Covariance between coordinates
- Depends on point sequence
back
55Finite Element Models
- Model variable objects as physical entities with
internal stiffness and elasticity - Build shapes from different modes of vibration
- Easy to construct compact parameterized shapes
next