Active%20Appearance%20Models - PowerPoint PPT Presentation

View by Category
About This Presentation
Title:

Active%20Appearance%20Models

Description:

[and partly on VisionSDK, LAPACK, Intel MKL, ImageMagick a.o.] Well documented ... well on very different segmentation problems and different image modalities ... – PowerPoint PPT presentation

Number of Views:14
Avg rating:3.0/5.0
Slides: 21
Provided by: MBS91
Learn more at: http://www2.imm.dtu.dk
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Active%20Appearance%20Models


1
Active Appearance Models
  • master thesis presentation
  • Mikkel B. Stegmann
  • IMM June 20th 2000

2
Presentation outline
  • Aim
  • Method
  • Metacarpals a case study
  • Discussion
  • Conclusion

3
Aim
  • To locate non-rigid objects in digital images
  • The vision utopia
  • Fully automated
  • General
  • Specific
  • Robust
  • Accurate
  • Holistic
  • Non-parametric
  • Fast

4
Active Appearance Models
  • A model-based approach towards segmentation
  • A priori knowledge is not programmed into the
    model, but learned through observation
  • Relies on statistical analysis of shape and
    texture variation in a training set
  • Derives a compact object class description which
    can be used to rapidly search images for new
    object instances

5
Model building
1) Data capture Shape point annotation Texture
pixel sampling
3) Combining shape and appearance Shape and
texture PCA is combined into a 3rd PCA
4) Model truncation Parameters are truncated to
satisfy a variance constraint
2) Normalisation Shape pose alignment using
the Procrustes shape metric Texture
photometric normalisation
3) Statistical analysis Principal component
analysis on shape and texture
6
Shape analysis
  • Shape is represented by a linear spline of
    landmarks
  • X ( x1, , xn, y1, , yn)T
  • Assumes point correlation
  • Requires point correspondence

Alignment w.r.t. position, scale, orientation
Principal component analysis
Compact shape representation
7
Texture analysis
  • Texture the intensities across the object is
    sampled inside the shape using a suitable warp
    function
  • Warp function A piece-wise affine warp using the
    Delaunay triangulation

g ( x1, , xn)T
Principal component analysis
Compact texture representation
8
Combined Model
  • Shape and texture is combined into a compact
    model representation
  • This representation is capable of derforming in a
    similar manner to what is observed in the
    training set
  • Thus making the model specific to the class of
    objects it represents
  • Generative (self-contained)

9
Model Optimisation
  • Deforms the AAM to fit the image being searched
  • Assumes a linear relationship between model
    parameters and the observed fit C RX
  • Solved using multivariate linear regression on
    a large set of experiments

10
Implementation
  • Open source C API based on the Windows
    platform and partly on VisionSDK, LAPACK, Intel
    MKL, ImageMagick a.o.
  • Well documented cross-referenced HTML and PDF
  • Fast using Intel BLAS for matrix handling and
    widely use of dynamic programming
  • Suitable for education research lots of visual
    and numerical documentation .m .avi .bmp
  • Example usage included in the form of a console
    interface

11
Metacarpals a case study
  • 20 x-ray images of the human hand supplied by
    Pronosco
  • Metacarpal 2, 3, 4 annotated using 50 points on
    each
  • Difficult segmentation problem due to large shape
    variability and the ambiguous nature of
    radiographs

12
Building the model
  • Annotation of set of training images
  • Capture of shape texture
  • Statistical analysis on shape texture

13
Modes of variation
Shape
Texture
Combined
14
Metacarpal AAM
  • Image modality radiographs (x-rays)
  • 20 images/shapes in training set
  • 300 points in shape model
  • 10.000 pixels in texture model
  • 95 variation explained using 16 model parameters

15
Search
16
Metacarpal results
  • Using automatic initialisation
  • Good mean location accuracy 0.98 pixel (point to
    border)
  • Acceptable mean texture fit 6.57 gray levels
    (byte range)
  • Difficult to locate the exact bone extents at
    the proximal and distal end

mean pt. errors
distal
proximal
17
Discussion
  • Hidden benefits
  • Automatic registration
  • Variance analysis (group/longitudinal studies)
  • Discrimination/interpretation using the model
    parameters
  • Weaknesses
  • Requires landmarks (point correspondence)
  • Can only deform texture by moving edge points
  • Not robust to large-scale texture noise

18
Discussion - contd
  • Image modalities on which AAMs has been evaluated
    successfully
  • Radiographs - x-rays of human hands
  • Normal gray scale images - hands, pork carcasses
  • MRI - human hearts
  • Initialisation has been added, thus making AAM a
    fully automated segmentation method
  • The AAM approach extends to 3D and multivariate
    imaging

19
Conclusion
  • AAM has been implemented and extended as a fully
    automated and data-driven approach towards image
    segmentation
  • AAM performs well on very different segmentation
    problems and different image modalities
  • Properties
  • General
  • Specific
  • Captures domain knowledge without the need for
    technical knowledge
  • Robust
  • Non-parametric
  • Self-contained
  • Fast

20
fin
  • http//www.imm.dtu.dk/aam
About PowerShow.com