SHAPE THEORY USING GEOMETRY OF QUOTIENT SPACES: STORY STORY SHAPE THEORY USING GEOMETRY OF QUOTIENT SPACES: STORY STORY ANUJ SRIVASTAVA Dept of Statistics.

Slides:



Advertisements
Similar presentations
Pattern Recognition and Machine Learning
Advertisements

Applications of one-class classification
VBM Voxel-based morphometry
Medical Image Registration Kumar Rajamani. Registration Spatial transform that maps points from one image to corresponding points in another image.
Developable Surface Fitting to Point Clouds Martin Peternell Computer Aided Geometric Design 21(2004) Reporter: Xingwang Zhang June 19, 2005.
Stochastic Systems Group Some Rambling (Müjdat) and Some More Serious Discussion (Ayres, Junmo, Walter) on Shape Priors.
Differential geometry I
Active Contours, Level Sets, and Image Segmentation
Richard G. Baraniuk Chinmay Hegde Sriram Nagaraj Go With The Flow A New Manifold Modeling and Learning Framework for Image Ensembles Aswin C. Sankaranarayanan.
Spherical Representation & Polyhedron Routing for Load Balancing in Wireless Sensor Networks Xiaokang Yu Xiaomeng Ban Wei Zeng Rik Sarkar Xianfeng David.
Extended Gaussian Images
1 Numerical Geometry of Non-Rigid Shapes Diffusion Geometry Diffusion geometry © Alexander & Michael Bronstein, © Michael Bronstein, 2010 tosca.cs.technion.ac.il/book.
Visual Recognition Tutorial
Alternatives to Spherical Microphone arrays: Hybrid Geometries Aastha Gupta & Prof. Thushara Abhayapala Applied Signal Processing CECS To be presented.
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
Parameter Estimation: Maximum Likelihood Estimation Chapter 3 (Duda et al.) – Sections CS479/679 Pattern Recognition Dr. George Bebis.
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
International Workshop on Computer Vision - Institute for Studies in Theoretical Physics and Mathematics, April , Tehran 1 I THE NATURAL PSEUDODISTANCE:
Correspondence & Symmetry
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
1 Numerical geometry of non-rigid shapes Spectral Methods Tutorial. Spectral Methods Tutorial 6 © Maks Ovsjanikov tosca.cs.technion.ac.il/book Numerical.
Non-Euclidean Embedding
Visual Recognition Tutorial
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
July 3, Department of Computer and Information Science (IDA) Linköpings universitet, Sweden Minimal sufficient statistic.
1 Numerical geometry of non-rigid shapes Non-Euclidean Embedding Non-Euclidean Embedding Lecture 6 © Alexander & Michael Bronstein tosca.cs.technion.ac.il/book.
Modern Navigation Thomas Herring
Today Wrap up of probability Vectors, Matrices. Calculus
Binary Variables (1) Coin flipping: heads=1, tails=0 Bernoulli Distribution.
Gender and 3D Facial Symmetry: What’s the Relationship ? Xia BAIQIANG (University Lille1/LIFL) Boulbaba Ben Amor (TELECOM Lille1/LIFL) Hassen Drira (TELECOM.
The Statistical Properties of Large Scale Structure Alexander Szalay Department of Physics and Astronomy The Johns Hopkins University.
Matching 3D Shapes Using 2D Conformal Representations Xianfeng Gu 1, Baba Vemuri 2 Computer and Information Science and Engineering, Gainesville, FL ,
Principles of Pattern Recognition
TEMPLATE BASED SHAPE DESCRIPTOR Raif Rustamov Department of Mathematics and Computer Science Drew University, Madison, NJ, USA.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
S. Kurtek 1, E. Klassen 2, Z. Ding 3, A. Srivastava 1 1 Florida State University Department of Statistics 2 Florida State University Department of Mathematics.
Enhanced Correspondence and Statistics for Structural Shape Analysis: Current Research Martin Styner Department of Computer Science and Psychiatry.
1 UNC, Stat & OR Nonnegative Matrix Factorization.
ECE 8443 – Pattern Recognition LECTURE 07: MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION Objectives: Class-Conditional Density The Multivariate Case General.
Feature based deformable registration of neuroimages using interest point and feature selection Leonid Teverovskiy Center for Automated Learning and Discovery.
Non-Euclidean Example: The Unit Sphere. Differential Geometry Formal mathematical theory Work with small ‘patches’ –the ‘patches’ look Euclidean Do calculus.
A New Method of Probability Density Estimation for Mutual Information Based Image Registration Ajit Rajwade, Arunava Banerjee, Anand Rangarajan. Dept.
Jeff J. Orchard, M. Stella Atkins School of Computing Science, Simon Fraser University Freire et al. (1) pointed out that least squares based registration.
Geometry of Shape Manifolds
A Flexible New Technique for Camera Calibration Zhengyou Zhang Sung Huh CSPS 643 Individual Presentation 1 February 25,
Review of Probability. Important Topics 1 Random Variables and Probability Distributions 2 Expected Values, Mean, and Variance 3 Two Random Variables.
Chapter 13 (Prototype Methods and Nearest-Neighbors )
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
Review of statistical modeling and probability theory Alan Moses ML4bio.
CONSTANT RATE OF CHANGE A comparison between the vertical and horizontal change. X is the independent variable Y is the dependent variable. CONSTANT RATE.
Level Set Segmentation ~ 9.37 Ki-Chang Kwak.
SigClust Statistical Significance of Clusters in HDLSS Data When is a cluster “really there”? Liu et al (2007), Huang et al (2014)
Université d’Ottawa / University of Ottawa 2003 Bio 8102A Applied Multivariate Biostatistics L4.1 Lecture 4: Multivariate distance measures l The concept.
Intrinsic Data Geometry from a Training Set
LECTURE 09: BAYESIAN ESTIMATION (Cont.)
LECTURE 03: DECISION SURFACES
Unsupervised Riemannian Clustering of Probability Density Functions
Morphing and Shape Processing
Chapter 3 Component Reliability Analysis of Structures.
Spectral Methods Tutorial 6 1 © Maks Ovsjanikov
Clustering (3) Center-based algorithms Fuzzy k-means
Dynamical Statistical Shape Priors for Level Set Based Tracking
Computational Neuroanatomy for Dummies
Multiple Change Point Detection for Symmetric Positive Definite Matrices Dehan Kong University of Toronto JSM 2018 July 30, 2018.
Presented by Kojo Essuman Ackah Spring 2018 STA 6557 Project
Machine Learning Math Essentials Part 2
Anatomical Measures John Ashburner
Probabilistic Surrogate Models
Computer Aided Geometric Design
Presentation transcript:

SHAPE THEORY USING GEOMETRY OF QUOTIENT SPACES: STORY STORY SHAPE THEORY USING GEOMETRY OF QUOTIENT SPACES: STORY STORY ANUJ SRIVASTAVA Dept of Statistics Florida State University

FRAMEWORK: WHAT CAN IT DO? 1.Pairwise distances between shapes. 2.Invariance to nuisance groups (re-parameterization) and result in pairwise registrations. 3.Definitions of means and covariances while respecting invariance. 4.Leads to probability distributions on appropriate manifolds. The probabilities can then be used to compare ensembles. 5.Principled approach for multiple registration (avoids separate cost functions for registration and distance – this is suboptimal). Comes with theoretical support – consistency of estimation. Analysis on Quotient Spaces of Manifolds

Riemannian metric allows us to compute distances between points using geodesic paths. Geodesic lengths are proper distances, i.e. satisfy all three requirements including the triangle inequality Distances are needed to define central moments. GENERAL RIEMANNIAN APPROACH

Samples determine sample statistics (Sample statistics are random) Estimate parameters for prob. from samples. Geodesics help define and compute means and covariances. Prob. are used to classify shapes, evaluate hypothesis, used as priors in future inferences. Typically, one does not use samples to define distances…. Otherwise “distances” will be random maps. Triangle inequality?? Question: What are type of manifolds/metrics are relevant for shape analysis of functions, curves and surfaces? GENERAL RIEMANNIAN APPROACH

REPRESENTATION SPACES: LDDMM Embed objects in background spaces planes and volumes Left group action of diffeos: The problem of analysis (distances, statistics, etc) is transferred to the group G. Solve for geodesics using the shooting method, e.g. Planes are deformed to match curves and volumes are deformed to match surfaces.

ALTERNATIVE: PARAMETRIC OBJECTS Consider objects as parameterized curves and surfaces Reparametrization group action of diffeos: These actions are NOT transitive. This is a nuisance group that needs to be removed (in addition to the usual scale and rigid motion). Form a quotient space: Need a Riemannian metric on the quotient space. Typically the one on the original space descends to the quotient space under certain conditions Geodesics are computed using a shooting method or path straightening. Registration problem is embedded in distance/geodesic calculation

IMPORTANT STRENGTH Registration problem is embedded in distance/geodesic calculation Pre-determined parameterizations are not optimal, need elasticity Optimal parameterization is determined during pair-wise matching Parameterization is effectively the registration process Uniformly-spaced pts Non-uniformly spaced pts Shape 1Shape 2

Shape 1 Shape 2 Shape 2, re-parameterized Optimal parameterization is determined during pair-wise matching Parameterization is effectively the registration process Registration problem is embedded in distance/geodesic calculation Pre-determined parameterizations are not optimal, need elasticity IMPORTANT STRENGTH

SECTIONS & ORTHOGONAL SECTIONS In cases where applicable, orthogonal sections are very useful in analysis on quotient spaces One can identify an orthogonal section S with the quotient space M/G In landmark-based shape analysis: the set centered configurations in an OS for the translation group the set of “unit norm” configurations is an OS for the scaling group. Their intersection is an OS for the joint action. No such orthogonal section exists for rotation or re-parameterization.

THREE PROBLEM AREAS OF INTERESTTHREE PROBLEM AREAS OF INTEREST 1.Shape analysis of real-valued functions on [0,1]: primary goal: joint registration of functions in a principled way 2. Shape analysis of curves in Euclidean spaces R n : primary goals: shape analysis of planar, closed curves shape analysis of open curves in R 3 shape analysis of curves in higher dimensions joint registration of multiple curves 3. Shape analysis of surfaces in R 3 : primary goals: shape analysis of closed surfaces (medical) shape analysis of disk-like surfaces (faces) shape analysis of quadrilateral surfaces (images) joint registration of multiple surfaces

MATHEMATICAL FRAMEWORK The overall distance between two shapes is given by: registration over rotation and parameterization finding geodesics using path straightening

Function data 1. ANALYSIS OF REAL-VALUED FUNCTIONS1. ANALYSIS OF REAL-VALUED FUNCTIONS Aligned functions “y variability” Warping functions “x variability”

1. ANALYSIS OF REAL-VALUED FUNCTIONS1. ANALYSIS OF REAL-VALUED FUNCTIONS Space: Group: Interested in Quotient space Riemannian Metric: Fisher-Rao metric Since the group action is by isometries, F-R metric descends to the quotient space. Square-Root Velocity Function (SRVF): Under SRVF, F-R metric becomes L 2 metric

MULTIPLE REGISTRATION PROBLEM

COMPARISONS WITH OTHER METHODS Original DataAUTC [4]SMR [3]MM [7]Our Method Simulated Datasets:

COMPARISONS WITH OTHER METHODS Original DataAUTC [4]SMR [3]MM [7]Our Method Real Datasets:

STUDIES ON DIFFICULT DATASETS (Steve Marron and Adelaide Proteomics Group)

A CONSISTENT ESTIMATOR OF SIGNAL A CONSISTENT ESTIMATOR OF SIGNAL Theorem 1: Karcher mean of is within a constant. Theorem 2: A specific element of that mean is a consistent estimator of g Goal: Given observed or, estimate or. Setup: Let

AN EXAMPLE OF SIGNAL ESTIMATION Original SignalObservations Aligned functions Estimated SignalError

2. SHAPE ANALYSIS OF CURVES2. SHAPE ANALYSIS OF CURVES Space: Group: Interested in Quotient space: (and rotation) Riemannian Metric: Elastic metric (Mio et al. 2007) Since the group action is by isometries, elastic metric descends to the quotient space. Square-Root Velocity Function (SRVF): Under SRVF, a particular elastic metric becomes L 2 metric

-- The distance between and is -- The solution comes from a gradient method. Dynamic programming is not applicable anymore. SHAPE SPACES OF CLOSED CURVES Closed Curves: -- The geodesics are obtained using a numerical procedure called path straightening.

GEODESICS BETWEEN SHAPES

IMPORTANCE OF ELASTIC ANALYSIS ElasticNon-Elastic Elastic Non-Elastic Elastic Non-Elastic Elastic

STATISTICAL SUMMARIES OF SHAPES Sample shapes Karcher Means: Comparisons with Other Methods Active Shape Models Kendall’s Shape Analysis Elastic Shape Analysis

WRAPPED DISTRIBUTIONS Choose a distribution in the tangent space and wrap it around the manifold Analytical expressions for truncated densities on spherical manifolds exponential stereographic Kurtek et al., Statistical Modeling of Curves using Shapes and Related Features, in review, JASA, 2011.

ANALYSIS OF PROTEIN BACKBONES Liu et al., Protein Structure Alignment Using Elastic Shape Analysis, ACM Conference on Bioinformatics, Clustering Performance

INFERENCES USING COVARIANCES Liu et al., A Mathematical Framework for Protein Structure Comparison, PLOS Computational Biology, February, Wrapped Normal Distribution

AUTOMATED CLUSTERING OF SHAPES Mani et al., A Comprehensive Riemannian Framework for Analysis of White Matter Fiber Tracts, ISBI, Rotterdam, The Netherlands, Shape, shape + orientation, shape + scale, shape + orientation + scale, …..

3. SHAPE ANALYSIS OF SURFACES3. SHAPE ANALYSIS OF SURFACES Space: Group: Interested in Quotient space: (and rotation) Riemannian Metric: Define q-map and choose L 2 metric Since the group action is by isometries, this metric descend to the quotient space. q-maps:

GEODESICS COMPUTATIONS Preshape Space

GEODESICSGEODESICS

COVARIANCE AND GAUSSIAN CLASSIFICATION Kurtek et al., Parameterization-Invariant Shape Statistics and Probabilistic Classification of Anatomical Surfaces, IPMI, 2011.

Different metrics and representations One should compare deformations (geodesics), summaries (mean and covariance), etc, under different methods. Systematic comparisons on real, annotated datasets Organize public databases and let people have a go at them. DISCUSSION POINTS

THANK YOU