SlideShare a Scribd company logo
Image Analysis & Retrieval
CS/EE 5590 Special Topics (Class Ids: 44873, 44874)
Fall 2016, M/W 4-5:15pm@Bloch 0012
Lec 17
Sparse Signal Processing & Applications
Zhu Li
Dept of CSEE, UMKC
Office: FH560E, Email: lizhu@umkc.edu, Ph: x 2346.
http://l.web.umkc.edu/lizhu
p.1Z. Li, Image Analysis & Retrv, 2016 Fall
Outline
 Recap:
 Piece-wise Linear Models via Query Driven Solution
 Subspace Indexing on Grassmann Manifold
 Optimization of Subspace on Grassmann Manifold
 Sparse Signal Processing
 Sparse Representation and Robust PCA
 Sparse Signal Processing
 L1 norm and L1 Magic Solution
 Application in occluded face recognition
 Summary
p.2Z. Li, Image Analysis & Retrv, 2016 Fall
Piece-wise Linear : Query Driven
• Query-Driven Piece-wise Linear Model
– No pre-determined structure on the training data
– Local neighborhood data patch identified from query point q,
– Local model built with local data, A(X, q)
p.3Z. Li, Image Analysis & Retrv, 2016 Fall
DPC – Discriminant Power Coefficient
 The tradeoffs in local data support size
p.4Z. Li, Image Analysis & Retrv, 2016 Fall
Face Recognition
 On ATT Data set: 40 subjects, 400 images:
Extra credit: 10pts 
 Develop a query driven local Laplacianface model for HW-3
p.5Z. Li, Image Analysis & Retrv, 2016 Fall
Subspace Indexing on Grassmann Manifold
• Subspace Clustering by Grassmann Metric:
– It is a VQ like process.
– Start with a data partition kd-tree, their leaf nodes and associated subspaces {Ak},
k=1..2h
– Repeat
» Find Ai and Aj, if darc(Ai, Aj) is the smallest among all, and the associated data
patch are adjacent in the data space.
» Delete Ai and Aj, replace with merged new subspace, and update associated data
patch leaf nodes set.
» Compute the empirical identification accuracy for the merged subspace
» Add parent pointer to the merged new subspace for Ai and Aj .
» Stop if only 1 subspace left.
p.6Z. Li, Image Analysis & Retrv, 2016 Fall
Simulation
• Face data set
– Mixed data set of 242 individuals, and 4840 face images
– Performance compared with PCA, LDA and LPP modeling
p.7Z. Li, Image Analysis & Retrv, 2016 Fall
Newtonian Method in Optimization
 Recall that in optimizing a functional over vector
variables f(X), X in Rn,
p.8
Credit: Kerstin Johnsson, Lund Univ
Z. Li, Image Analysis & Retrv, 2016 Fall
Gradient & Hessian on Grassmann Manifold
 Gradient on Grassmann manifold:
p.9Z. Li, Image Analysis & Retrv, 2016 Fall
Hessian on Grassmann Manifold
 Hessian:
 FY = nxp 1st order differentiation
 FYY= 2nd order differentiation along Y
p.10Z. Li, Image Analysis & Retrv, 2016 Fall
Newton’s Method on Grassmann Manifold
 Overall framework
Prof. A. Edelman’s matlab package:
 https://umkc.box.com/s/g2oyqvsb2lx2v9wzf0ju60wnspts4t9g
p.11Z. Li, Image Analysis & Retrv, 2016 Fall
Outline
 Recap:
 Piece-wise Linear Models via Query Driven Solution
 Subspace Indexing on Grassmann Manifold
 Optimization of Subspace on Grassmann Manifold
 Sparse Signal Processing
 Sparse Representation and Robust PCA
 Sparse Signal Processing
 L1 norm and L1 Magic Solution
 Application in occluded face recognition
 Summary
p.12Z. Li, Image Analysis & Retrv, 2016 Fall
Sparse representation
• Signals/Images are sparse if it can have very few non-zero
coefficients representation in certain subspace:
– E.g. cameraman image X represented as 2-D DCT in Y:
• How is this related to classification problem ?
– Intuitively, sparse is good for classification, because it is to
separate samples from different classes
– Only when data points are dense and intertwined , classification is
hard
– How to characterize this mathematically ? 
x y=dct2(x)
Eigen face
p.13Z. Li, Image Analysis & Retrv, 2016 Fall
Sparsity in Human Visual System
p.14Z. Li, Image Analysis & Retrv, 2016 Fall
Sparse Signal Recovery
 If x is sparse, i.e |x|0 is small, we can recovery x by a
random projection measurement, y=Ax
 Basis pursuit de-noising:
 LASSO:
p.15Z. Li, Image Analysis & Retrv, 2016 Fall
Sparse Face Model
Consider a face recognition system
 We have k=1,2,…,K subjects, each subject has nk training samples
{[v1,1, .., v1,n1], [v2,1, .., v2,n2], …, [vK,1, .., vK,nK]}, each is a
thumbnail image with d=wxh pixels.
 Let us stack all training samples as a collection of column vectors,
A, of d N, N=n1 + n2 + … + nK.
 The problem is, for a given thumbnail image, y, with unknown
class label, how to solve for its label ?K
p.16Z. Li, Image Analysis & Retrv, 2016 Fall
Assume y is belonging to class i, then,
Or,
Where only a small number of coefficients in x has non-zero entry, thus sparse.
Sparsity
p.17Z. Li, Image Analysis & Retrv, 2016 Fall
Assume y is belonging to class 1, then,
Most co-efficients related to other classes are zero, only a small
number of non-zero coefficients in alpha 1
Illustration of Sparsity
p.18Z. Li, Image Analysis & Retrv, 2016 Fall
• So the problem is rather straight forward
– Give y = Ax, where
• y is the unknown face image in Rd,
• A is the d x N training data matrix, or dictionary, with N large
• x is the coefficients of y as linear combination of training
samples that is sparse, out of total N coefficients, only a small
number of them are non-zero
– Mathematically, we are looking for :
• Where |x|0 is L0 norm, which counts number of non-zero
coefficients in x.
Mathematical formulation
𝑥0 = arg min
𝑥
𝑥 0, 𝑠. 𝑡. , 𝐴𝑥 = 𝑦
p.19Z. Li, Image Analysis & Retrv, 2016 Fall
• The L0 minimization problem is basically a
combinatorial optimization problem
• Not much structure to exploit fast algorithm
• Dumbest solution:
– Assuming that x has at most 3 non-zero coefficients, then
search total
– Possible coefficients combinations and find the one gives
the best match
– It is an kNN search in effect !
L0 minimization is NP hard
𝑁
1
+
𝑁
2
+
𝑁
3
p.20Z. Li, Image Analysis & Retrv, 2016 Fall
L0 and L1 norm
 Lk norm (recall minkowski distance)
p.21Z. Li, Image Analysis & Retrv, 2016 Fall
L1 solution
L-2 ball
p.22Z. Li, Image Analysis & Retrv, 2016 Fall
L1 based recognition
p.23Z. Li, Image Analysis & Retrv, 2016 Fall
L1 solution for invalid input images
• For non-face images:
– Non sparse coefficients in x
• Can threshold on residual to return not found result
p.24Z. Li, Image Analysis & Retrv, 2016 Fall
Occlusion and Disguise
• A big problem in biometrics is disguise and occlusion
• The magic of sparsity and L1 minimization can deal with
that effectively !
• Consider a face image with a small fraction p of its pixels
corrupted:
p.25Z. Li, Image Analysis & Retrv, 2016 Fall
• Let the occluded face images be y = Ax + e
• Then re-state the constraint as,
• then solve for P1 with y=Bw. Notice that sparsity in w is
achieved thru sparsity in both x and e.
Sparsity criteria takes care of occlusion
p.26Z. Li, Image Analysis & Retrv, 2016 Fall
• Occlusion example
– Large L2 errors, not recoverable by Eigenface/Fisherface:
• Accuracy for sunglasses and scarves effects:
Occluded face recognition
p.27Z. Li, Image Analysis & Retrv, 2016 Fall
L1 vs L2 minimization
• A natural question is why not solve y=Ax with L2
minimization ?
– Typically, number of training samples is smaller than number of pixels
in the training images, so why not do a pseudo-inverse like:
– Which looks for a Maximum Likelihood estimation of true x, if noises
are Gaussian with covariance sI.
– However, the noises are non-gaussian and can be unbounded. The
resulting L2 solution pretty bad
p.28Z. Li, Image Analysis & Retrv, 2016 Fall
L2 solution for Occlusion
• Example with occlusion:
– (a): Occluded face
– (b): x solved from L2 minimization, not sparse at all
– (c ): error
– (d ): reconstruction from x
p.29Z. Li, Image Analysis & Retrv, 2016 Fall
L1 vs L2 minimization
L1 vs L2 in 2D space:
y=Ax
p.30Z. Li, Image Analysis & Retrv, 2016 Fall
Sparsity is bad news for L2
• Given training set A, the unknown image y is under-
determined in A:
– R(A): a set of y that satisfies y=Ax:
p.31Z. Li, Image Analysis & Retrv, 2016 Fall
Numeric solution for L1 minimization
Candes (of CalTech)’s group has this L1 magic matlab
toolbox
 Check out manual on course webpage
 Stephen Boyd:
 Boyd’s nice book on Optimization can be downloaded from
his webpage at Stanford.
 Excellent book, with slides, homework and solutions.
 https://web.stanford.edu/~boyd/cvxbook/bv_cvxbook.pdf
p.32Z. Li, Image Analysis & Retrv, 2016 Fall
Numerical Tool from L1 Magic
 L1 Magic Toolbox:
p.33
% signal length
N = 512;
% number of spikes in the signal, must be sparse w.r.t N
T = 20;
% number of observations to make
K = 120;
% random +/- 1 signal
x = zeros(N,1);
q = randperm(N);
x(q(1:T)) = sign(randn(T,1));
subplot(3,1,1); plot(x); title('x(t)'); axis([1 500 -1.2 1.2]);
% measurement matrix: random measuring
fprintf('n Creating random measurement matrix...');
A = randn(K,N);
% othorgonalize
A = orth(A')';
% observations
y = A*x;
% initial guess = min energy
x0 = A'*y;
subplot(3,1,2); plot(x0); title('x_0(t)'); axis([1 500 -1.2 1.2]);
% solve with primal-dual method
xp = l1eq_pd(x0, A, [], y, 1e-3);
subplot(3,1,3); plot(xp); title('x(t) recovered by L1 magic'); axis([1 500 -1.2 1.2]);
% test l1magic
end
Z. Li, Image Analysis & Retrv, 2016 Fall
L1 Magic demo
50 100 150 200 250 300 350 400 450 500
-1
0
1
x(t)
50 100 150 200 250 300 350 400 450 500
-1
0
1
x0(t)
50 100 150 200 250 300 350 400 450 500
-1
0
1
x(t) recovered by l1 magic
Original sparse signal
L1 magic recovered
sparse signal
Pseudo-inverse: L2 recovery
p.34Z. Li, Image Analysis & Retrv, 2016 Fall
Sparse face
 Recover face as sparse signal
p.35
% create our measure matrix A: face + nonface icons
A=zeros(1600, w*h);
A(1:400, :) = faces; A(401:1600, :) = nfaces;
[N, dim]=size(A);
% in col vec form
A = A';
% pick a face: offs in 1-400
figure(3); colormap('gray');
offs = 20; y = faces(offs, :)';
subplot(2,2,1); axis off; imagesc(reshape(y, h,w)); title('fontsize{11}original');
% solve for xp = min |x|, s.t. y=Ax
% initial guess = min energy
x0 = A'*y;
% solve with primal-dual method
xp = l1eq_pd(x0, A, [], y, 1e-3);
% normalize
x0 = x0./norm(x0);
xp = xp./norm(xp);
% reconstructed face
yp = A*xp;
subplot(2,2,2); axis off; imagesc(reshape(yp, h,w)); title('fontsize{11}sparse
reconstruction');
Z. Li, Image Analysis & Retrv, 2016 Fall
L1Magic for Face Recognition
p.36Z. Li, Image Analysis & Retrv, 2016 Fall
Super Resolution
Super-Resolution
 Super-resolves a lower
resolution patch, say k x k,
to 3k x 3k.
 Mathematically, learn a
function:
p.37
𝑓 𝑥 → 𝑌, 𝑥 ∈ 𝑅 𝑑, 𝑌 ∈ 𝑅 𝐷
Z. Li, Image Analysis & Retrv, 2016 Fall
Basic Framework
 Super-resolve is the inverse of down scaling:
 Low res patch y is the blurred and scaled high res patch x:
 Assume the high res image is sparse on some dictionary (true,
say DCT):
p.38
Output OriginalInput
Training patches
≈
𝑦 = 𝑆𝐻𝑥
Z. Li, Image Analysis & Retrv, 2016 Fall
Coupled Dictionary Learning
 Pre-train a common set of coupled low and high
resolution dictionary
 Super-resolve by solving L1 minimization on lower
resolution patch, and use the same coeffiients to
superresolve the higher resolution patch
p.39Z. Li, Image Analysis & Retrv, 2016 Fall
Coupled Dictionary Learning
 Learn two sets of Dictionaries, Dh, Dl, that have
common sparse coefficients for low and high resolution
image patches, y and x:
 Reconstruction of low res patch with sparse coefficients:
 Furthermore, introduce a linear projection, F, to enforce
perceptual metrics
 Then the high res patch x, can be constructed as
p.40
min 𝛼 0
, 𝑠. 𝑡. , 𝐷𝑙 𝛼 − 𝑦
2
≤ 𝜖
min 𝛼 0
, 𝑠. 𝑡. , 𝐹𝐷𝑙 𝛼 − 𝐹𝑦
2
≤ 𝜖
𝑥 = 𝐷ℎ 𝛼
Yang, J Wright, TS Huang, Y Ma, Image super-resolution via sparse representation, IEEE Trans.
Image Processing, vol.19 (11), 2861-2873
Z. Li, Image Analysis & Retrv, 2016 Fall
Coupled Dictionary Learning
 Put together, super resolve is to solve:
 Sparse reconstruction of lower resolution y
 Enforce local consistence with high res patches, extract
adjacent overlapping stripes, via P, to be in agreement, w is
the previously reconstructed patch pixels:
 Solution via Lagrangian relaxation:
p.41Z. Li, Image Analysis & Retrv, 2016 Fall
Overall Algorithm
 Patch level super-resolution, complete with global
image gradient search
p.42Z. Li, Image Analysis & Retrv, 2016 Fall
Dictionary Training
Training data: low and high
resolution image patches Yl={yk},
Xh={xk}:
 Enforce the common sparse
coefficients
p.43Z. Li, Image Analysis & Retrv, 2016 Fall
Results
 Dictionary Training
 From flowers and animals data set, covering a variety
of texture
 Training dictionary from more than 100,000
samples
p.44
𝐷ℎ
𝐷𝑙
Z. Li, Image Analysis & Retrv, 2016 Fall
Results
 3x super-resolution
p.45
Bicubic Neighbor embedding
[Chang CVPR ‘04]
Low-resolution
input
OriginalCoupled Dictionary
Z. Li, Image Analysis & Retrv, 2016 Fall
Related Work
 Potential paper review project
p.46Z. Li, Image Analysis & Retrv, 2016 Fall
Summary
 Sparse Signal Processing
 If signal is sparse in some (unknown) domain, then from a random measurement,
we can reliably recover the signal via L1 minimization
 Applications: Robust PCA and Face Recognition with Occlusion
 Face images are sparse linear combination from a face dictionary
 Recovery from solving L1 problem ~ caveat: only additive noises can be delt.
 Applications: Coupled Dictionary for Image Super Resolution
 Coupled dictionary: high and low res image patches sharing the same coefficients.
p.47
min
𝑥
𝑥 1, 𝑠. 𝑡. 𝑦 = 𝐴𝑥
Z. Li, Image Analysis & Retrv, 2016 Fall

More Related Content

What's hot

M ary psk modulation
M ary psk modulationM ary psk modulation
M ary psk modulation
Ahmed Diaa
 
MIMO Channel Capacity
MIMO Channel CapacityMIMO Channel Capacity
MIMO Channel Capacity
Pei-Che Chang
 
Adaptive filter
Adaptive filterAdaptive filter
Adaptive filter
A. Shamel
 
Source coding
Source coding Source coding
Source coding
Shankar Gangaju
 
Digital Image Processing - Image Restoration
Digital Image Processing - Image RestorationDigital Image Processing - Image Restoration
Digital Image Processing - Image Restoration
Mathankumar S
 
Fir and iir filter_design
Fir and iir filter_designFir and iir filter_design
Fir and iir filter_designshrinivasgnaik
 
Wavelet Transform and DSP Applications
Wavelet Transform and DSP ApplicationsWavelet Transform and DSP Applications
Wavelet Transform and DSP Applications
University of Technology - Iraq
 
4.4 diversity combining techniques
4.4   diversity combining techniques4.4   diversity combining techniques
4.4 diversity combining techniques
JAIGANESH SEKAR
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image Fundamentals
A B Shinde
 
Smoothing in Digital Image Processing
Smoothing in Digital Image ProcessingSmoothing in Digital Image Processing
Smoothing in Digital Image Processing
Pallavi Agarwal
 
Image segmentation
Image segmentation Image segmentation
Spatial filtering
Spatial filteringSpatial filtering
Spatial filtering
shabanam tamboli
 
Learning Sparse Representation
Learning Sparse RepresentationLearning Sparse Representation
Learning Sparse Representation
Gabriel Peyré
 
Digital Signal Processing
Digital Signal ProcessingDigital Signal Processing
Digital Signal Processing
Sandip Ladi
 
Adaptive equalization
Adaptive equalizationAdaptive equalization
Adaptive equalization
Oladapo Abiodun
 
Introductions to Online Machine Learning Algorithms
Introductions to Online Machine Learning AlgorithmsIntroductions to Online Machine Learning Algorithms
Introductions to Online Machine Learning Algorithms
DataWorks Summit
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image Fundamentals
Mostafa G. M. Mostafa
 
Lec3: Pre-Processing Medical Images
Lec3: Pre-Processing Medical ImagesLec3: Pre-Processing Medical Images
Lec3: Pre-Processing Medical Images
Ulaş Bağcı
 

What's hot (20)

M ary psk modulation
M ary psk modulationM ary psk modulation
M ary psk modulation
 
MIMO Channel Capacity
MIMO Channel CapacityMIMO Channel Capacity
MIMO Channel Capacity
 
Adaptive filter
Adaptive filterAdaptive filter
Adaptive filter
 
Source coding
Source coding Source coding
Source coding
 
Digital Image Processing - Image Restoration
Digital Image Processing - Image RestorationDigital Image Processing - Image Restoration
Digital Image Processing - Image Restoration
 
Fir and iir filter_design
Fir and iir filter_designFir and iir filter_design
Fir and iir filter_design
 
Wavelet Transform and DSP Applications
Wavelet Transform and DSP ApplicationsWavelet Transform and DSP Applications
Wavelet Transform and DSP Applications
 
4.4 diversity combining techniques
4.4   diversity combining techniques4.4   diversity combining techniques
4.4 diversity combining techniques
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image Fundamentals
 
Smoothing in Digital Image Processing
Smoothing in Digital Image ProcessingSmoothing in Digital Image Processing
Smoothing in Digital Image Processing
 
Image segmentation
Image segmentation Image segmentation
Image segmentation
 
Spatial filtering
Spatial filteringSpatial filtering
Spatial filtering
 
Array antennas
Array antennasArray antennas
Array antennas
 
Learning Sparse Representation
Learning Sparse RepresentationLearning Sparse Representation
Learning Sparse Representation
 
Digital Signal Processing
Digital Signal ProcessingDigital Signal Processing
Digital Signal Processing
 
Arithmetic Coding
Arithmetic CodingArithmetic Coding
Arithmetic Coding
 
Adaptive equalization
Adaptive equalizationAdaptive equalization
Adaptive equalization
 
Introductions to Online Machine Learning Algorithms
Introductions to Online Machine Learning AlgorithmsIntroductions to Online Machine Learning Algorithms
Introductions to Online Machine Learning Algorithms
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image Fundamentals
 
Lec3: Pre-Processing Medical Images
Lec3: Pre-Processing Medical ImagesLec3: Pre-Processing Medical Images
Lec3: Pre-Processing Medical Images
 

Viewers also liked

20150414seminar
20150414seminar20150414seminar
20150414seminar
nlab_utokyo
 
Compressive Sensing Basics - Medical Imaging - MRI
Compressive Sensing Basics - Medical Imaging - MRICompressive Sensing Basics - Medical Imaging - MRI
Compressive Sensing Basics - Medical Imaging - MRI
Thomas Stefani
 
Introduction to compressive sensing
Introduction to compressive sensingIntroduction to compressive sensing
Introduction to compressive sensing
Ahmed Nasser Agag
 
Ppt compressed sensing a tutorial
Ppt compressed sensing a tutorialPpt compressed sensing a tutorial
Ppt compressed sensing a tutorial
Terence Gao
 
Introduction to Compressive Sensing (Compressed Sensing)
Introduction to Compressive Sensing (Compressed Sensing)Introduction to Compressive Sensing (Compressed Sensing)
Introduction to Compressive Sensing (Compressed Sensing)
Hamid Adldoost
 
Introduction to compressive sensing
Introduction to compressive sensingIntroduction to compressive sensing
Introduction to compressive sensingMohammed Musfir N N
 
スパースモデリング入門
スパースモデリング入門スパースモデリング入門
スパースモデリング入門
Hideo Terada
 

Viewers also liked (8)

Sparse representation and compressive sensing
Sparse representation and compressive sensingSparse representation and compressive sensing
Sparse representation and compressive sensing
 
20150414seminar
20150414seminar20150414seminar
20150414seminar
 
Compressive Sensing Basics - Medical Imaging - MRI
Compressive Sensing Basics - Medical Imaging - MRICompressive Sensing Basics - Medical Imaging - MRI
Compressive Sensing Basics - Medical Imaging - MRI
 
Introduction to compressive sensing
Introduction to compressive sensingIntroduction to compressive sensing
Introduction to compressive sensing
 
Ppt compressed sensing a tutorial
Ppt compressed sensing a tutorialPpt compressed sensing a tutorial
Ppt compressed sensing a tutorial
 
Introduction to Compressive Sensing (Compressed Sensing)
Introduction to Compressive Sensing (Compressed Sensing)Introduction to Compressive Sensing (Compressed Sensing)
Introduction to Compressive Sensing (Compressed Sensing)
 
Introduction to compressive sensing
Introduction to compressive sensingIntroduction to compressive sensing
Introduction to compressive sensing
 
スパースモデリング入門
スパースモデリング入門スパースモデリング入門
スパースモデリング入門
 

Similar to Lec17 sparse signal processing & applications

Lec14 eigenface and fisherface
Lec14 eigenface and fisherfaceLec14 eigenface and fisherface
Lec14 eigenface and fisherface
United States Air Force Academy
 
Lec15 graph laplacian embedding
Lec15 graph laplacian embeddingLec15 graph laplacian embedding
Lec15 graph laplacian embedding
United States Air Force Academy
 
Lec16 subspace optimization
Lec16 subspace optimizationLec16 subspace optimization
Lec16 subspace optimization
United States Air Force Academy
 
Face recognition using laplacianfaces (synopsis)
Face recognition using laplacianfaces (synopsis)Face recognition using laplacianfaces (synopsis)
Face recognition using laplacianfaces (synopsis)Mumbai Academisc
 
Lec07 aggregation-and-retrieval-system
Lec07 aggregation-and-retrieval-systemLec07 aggregation-and-retrieval-system
Lec07 aggregation-and-retrieval-system
United States Air Force Academy
 
Moshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenfaceMoshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenfacewolf
 
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsMethods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Ryan B Harvey, CSDP, CSM
 
Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification
Subspace Indexing on Grassmannian Manifold for Large Scale Visual IdentificationSubspace Indexing on Grassmannian Manifold for Large Scale Visual Identification
Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification
United States Air Force Academy
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
IJERD Editor
 
Ridge regression
Ridge regressionRidge regression
Ridge regression
Ananda Swarup
 
On image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDAOn image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDA
Raghu Palakodety
 
STUDY OF Ε-SMOOTH SUPPORT VECTOR REGRESSION AND COMPARISON WITH Ε- SUPPORT ...
STUDY OF Ε-SMOOTH SUPPORT VECTOR  REGRESSION AND COMPARISON WITH Ε- SUPPORT  ...STUDY OF Ε-SMOOTH SUPPORT VECTOR  REGRESSION AND COMPARISON WITH Ε- SUPPORT  ...
STUDY OF Ε-SMOOTH SUPPORT VECTOR REGRESSION AND COMPARISON WITH Ε- SUPPORT ...
ijscai
 
Nonlinear Manifolds in Computer Vision
Nonlinear Manifolds in Computer VisionNonlinear Manifolds in Computer Vision
Nonlinear Manifolds in Computer Visionzukun
 
Sequential Probability Ratio Test for Sparse Signals
Sequential Probability Ratio Test for Sparse SignalsSequential Probability Ratio Test for Sparse Signals
Sequential Probability Ratio Test for Sparse Signals
Mohamed Seif
 
B02402012022
B02402012022B02402012022
B02402012022
inventionjournals
 
Distributed Architecture of Subspace Clustering and Related
Distributed Architecture of Subspace Clustering and RelatedDistributed Architecture of Subspace Clustering and Related
Distributed Architecture of Subspace Clustering and Related
Pei-Che Chang
 
Face Recognition using PCA-Principal Component Analysis using MATLAB
Face Recognition using PCA-Principal Component Analysis using MATLABFace Recognition using PCA-Principal Component Analysis using MATLAB
Face Recognition using PCA-Principal Component Analysis using MATLAB
Sindhi Madhuri
 
Face recognition using PCA
Face recognition using PCAFace recognition using PCA
Face recognition using PCA
Nawin Kumar Sharma
 
Spectral Clustering Report
Spectral Clustering ReportSpectral Clustering Report
Spectral Clustering ReportMiaolan Xie
 
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transferMLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
Charles Deledalle
 

Similar to Lec17 sparse signal processing & applications (20)

Lec14 eigenface and fisherface
Lec14 eigenface and fisherfaceLec14 eigenface and fisherface
Lec14 eigenface and fisherface
 
Lec15 graph laplacian embedding
Lec15 graph laplacian embeddingLec15 graph laplacian embedding
Lec15 graph laplacian embedding
 
Lec16 subspace optimization
Lec16 subspace optimizationLec16 subspace optimization
Lec16 subspace optimization
 
Face recognition using laplacianfaces (synopsis)
Face recognition using laplacianfaces (synopsis)Face recognition using laplacianfaces (synopsis)
Face recognition using laplacianfaces (synopsis)
 
Lec07 aggregation-and-retrieval-system
Lec07 aggregation-and-retrieval-systemLec07 aggregation-and-retrieval-system
Lec07 aggregation-and-retrieval-system
 
Moshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenfaceMoshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenface
 
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsMethods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
 
Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification
Subspace Indexing on Grassmannian Manifold for Large Scale Visual IdentificationSubspace Indexing on Grassmannian Manifold for Large Scale Visual Identification
Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
 
Ridge regression
Ridge regressionRidge regression
Ridge regression
 
On image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDAOn image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDA
 
STUDY OF Ε-SMOOTH SUPPORT VECTOR REGRESSION AND COMPARISON WITH Ε- SUPPORT ...
STUDY OF Ε-SMOOTH SUPPORT VECTOR  REGRESSION AND COMPARISON WITH Ε- SUPPORT  ...STUDY OF Ε-SMOOTH SUPPORT VECTOR  REGRESSION AND COMPARISON WITH Ε- SUPPORT  ...
STUDY OF Ε-SMOOTH SUPPORT VECTOR REGRESSION AND COMPARISON WITH Ε- SUPPORT ...
 
Nonlinear Manifolds in Computer Vision
Nonlinear Manifolds in Computer VisionNonlinear Manifolds in Computer Vision
Nonlinear Manifolds in Computer Vision
 
Sequential Probability Ratio Test for Sparse Signals
Sequential Probability Ratio Test for Sparse SignalsSequential Probability Ratio Test for Sparse Signals
Sequential Probability Ratio Test for Sparse Signals
 
B02402012022
B02402012022B02402012022
B02402012022
 
Distributed Architecture of Subspace Clustering and Related
Distributed Architecture of Subspace Clustering and RelatedDistributed Architecture of Subspace Clustering and Related
Distributed Architecture of Subspace Clustering and Related
 
Face Recognition using PCA-Principal Component Analysis using MATLAB
Face Recognition using PCA-Principal Component Analysis using MATLABFace Recognition using PCA-Principal Component Analysis using MATLAB
Face Recognition using PCA-Principal Component Analysis using MATLAB
 
Face recognition using PCA
Face recognition using PCAFace recognition using PCA
Face recognition using PCA
 
Spectral Clustering Report
Spectral Clustering ReportSpectral Clustering Report
Spectral Clustering Report
 
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transferMLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
 

More from United States Air Force Academy

Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super VectorLec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
United States Air Force Academy
 
Lec11 object-re-id
Lec11 object-re-idLec11 object-re-id
Lec12 review-part-i
Lec12 review-part-iLec12 review-part-i
Lec12 review-part-i
United States Air Force Academy
 
Lec11 rate distortion optimization
Lec11 rate distortion optimizationLec11 rate distortion optimization
Lec11 rate distortion optimization
United States Air Force Academy
 
Lec-03 Entropy Coding I: Hoffmann & Golomb Codes
Lec-03 Entropy Coding I: Hoffmann & Golomb CodesLec-03 Entropy Coding I: Hoffmann & Golomb Codes
Lec-03 Entropy Coding I: Hoffmann & Golomb Codes
United States Air Force Academy
 
Multimedia Communication Lec02: Info Theory and Entropy
Multimedia Communication Lec02: Info Theory and EntropyMultimedia Communication Lec02: Info Theory and Entropy
Multimedia Communication Lec02: Info Theory and Entropy
United States Air Force Academy
 
ECE 4490 Multimedia Communication Lec01
ECE 4490 Multimedia Communication Lec01ECE 4490 Multimedia Communication Lec01
ECE 4490 Multimedia Communication Lec01
United States Air Force Academy
 
Mobile Visual Search: Object Re-Identification Against Large Repositories
Mobile Visual Search: Object Re-Identification Against Large RepositoriesMobile Visual Search: Object Re-Identification Against Large Repositories
Mobile Visual Search: Object Re-Identification Against Large Repositories
United States Air Force Academy
 
Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting
Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 MeetingTutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting
Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting
United States Air Force Academy
 
Light Weight Fingerprinting for Video Playback Verification in MPEG DASH
Light Weight Fingerprinting for Video Playback Verification in MPEG DASHLight Weight Fingerprinting for Video Playback Verification in MPEG DASH
Light Weight Fingerprinting for Video Playback Verification in MPEG DASH
United States Air Force Academy
 
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...United States Air Force Academy
 

More from United States Air Force Academy (11)

Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super VectorLec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
 
Lec11 object-re-id
Lec11 object-re-idLec11 object-re-id
Lec11 object-re-id
 
Lec12 review-part-i
Lec12 review-part-iLec12 review-part-i
Lec12 review-part-i
 
Lec11 rate distortion optimization
Lec11 rate distortion optimizationLec11 rate distortion optimization
Lec11 rate distortion optimization
 
Lec-03 Entropy Coding I: Hoffmann & Golomb Codes
Lec-03 Entropy Coding I: Hoffmann & Golomb CodesLec-03 Entropy Coding I: Hoffmann & Golomb Codes
Lec-03 Entropy Coding I: Hoffmann & Golomb Codes
 
Multimedia Communication Lec02: Info Theory and Entropy
Multimedia Communication Lec02: Info Theory and EntropyMultimedia Communication Lec02: Info Theory and Entropy
Multimedia Communication Lec02: Info Theory and Entropy
 
ECE 4490 Multimedia Communication Lec01
ECE 4490 Multimedia Communication Lec01ECE 4490 Multimedia Communication Lec01
ECE 4490 Multimedia Communication Lec01
 
Mobile Visual Search: Object Re-Identification Against Large Repositories
Mobile Visual Search: Object Re-Identification Against Large RepositoriesMobile Visual Search: Object Re-Identification Against Large Repositories
Mobile Visual Search: Object Re-Identification Against Large Repositories
 
Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting
Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 MeetingTutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting
Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting
 
Light Weight Fingerprinting for Video Playback Verification in MPEG DASH
Light Weight Fingerprinting for Video Playback Verification in MPEG DASHLight Weight Fingerprinting for Video Playback Verification in MPEG DASH
Light Weight Fingerprinting for Video Playback Verification in MPEG DASH
 
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
 

Recently uploaded

BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...
BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...
BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...
Nguyen Thanh Tu Collection
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
Special education needs
 
Unit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdfUnit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdf
Thiyagu K
 
A Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptxA Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptx
thanhdowork
 
Biological Screening of Herbal Drugs in detailed.
Biological Screening of Herbal Drugs in detailed.Biological Screening of Herbal Drugs in detailed.
Biological Screening of Herbal Drugs in detailed.
Ashokrao Mane college of Pharmacy Peth-Vadgaon
 
Chapter 3 - Islamic Banking Products and Services.pptx
Chapter 3 - Islamic Banking Products and Services.pptxChapter 3 - Islamic Banking Products and Services.pptx
Chapter 3 - Islamic Banking Products and Services.pptx
Mohd Adib Abd Muin, Senior Lecturer at Universiti Utara Malaysia
 
The Diamond Necklace by Guy De Maupassant.pptx
The Diamond Necklace by Guy De Maupassant.pptxThe Diamond Necklace by Guy De Maupassant.pptx
The Diamond Necklace by Guy De Maupassant.pptx
DhatriParmar
 
Best Digital Marketing Institute In NOIDA
Best Digital Marketing Institute In NOIDABest Digital Marketing Institute In NOIDA
Best Digital Marketing Institute In NOIDA
deeptiverma2406
 
South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)
Academy of Science of South Africa
 
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdfMASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
goswamiyash170123
 
Digital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments UnitDigital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments Unit
chanes7
 
How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17
Celine George
 
Advantages and Disadvantages of CMS from an SEO Perspective
Advantages and Disadvantages of CMS from an SEO PerspectiveAdvantages and Disadvantages of CMS from an SEO Perspective
Advantages and Disadvantages of CMS from an SEO Perspective
Krisztián Száraz
 
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptxChapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Mohd Adib Abd Muin, Senior Lecturer at Universiti Utara Malaysia
 
Operation Blue Star - Saka Neela Tara
Operation Blue Star   -  Saka Neela TaraOperation Blue Star   -  Saka Neela Tara
Operation Blue Star - Saka Neela Tara
Balvir Singh
 
Azure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHatAzure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHat
Scholarhat
 
CACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdfCACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdf
camakaiclarkmusic
 
Francesca Gottschalk - How can education support child empowerment.pptx
Francesca Gottschalk - How can education support child empowerment.pptxFrancesca Gottschalk - How can education support child empowerment.pptx
Francesca Gottschalk - How can education support child empowerment.pptx
EduSkills OECD
 
S1-Introduction-Biopesticides in ICM.pptx
S1-Introduction-Biopesticides in ICM.pptxS1-Introduction-Biopesticides in ICM.pptx
S1-Introduction-Biopesticides in ICM.pptx
tarandeep35
 
How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...
Jisc
 

Recently uploaded (20)

BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...
BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...
BÀI TẬP BỔ TRỢ TIẾNG ANH GLOBAL SUCCESS LỚP 3 - CẢ NĂM (CÓ FILE NGHE VÀ ĐÁP Á...
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
 
Unit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdfUnit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdf
 
A Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptxA Survey of Techniques for Maximizing LLM Performance.pptx
A Survey of Techniques for Maximizing LLM Performance.pptx
 
Biological Screening of Herbal Drugs in detailed.
Biological Screening of Herbal Drugs in detailed.Biological Screening of Herbal Drugs in detailed.
Biological Screening of Herbal Drugs in detailed.
 
Chapter 3 - Islamic Banking Products and Services.pptx
Chapter 3 - Islamic Banking Products and Services.pptxChapter 3 - Islamic Banking Products and Services.pptx
Chapter 3 - Islamic Banking Products and Services.pptx
 
The Diamond Necklace by Guy De Maupassant.pptx
The Diamond Necklace by Guy De Maupassant.pptxThe Diamond Necklace by Guy De Maupassant.pptx
The Diamond Necklace by Guy De Maupassant.pptx
 
Best Digital Marketing Institute In NOIDA
Best Digital Marketing Institute In NOIDABest Digital Marketing Institute In NOIDA
Best Digital Marketing Institute In NOIDA
 
South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)
 
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdfMASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
 
Digital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments UnitDigital Artifact 1 - 10VCD Environments Unit
Digital Artifact 1 - 10VCD Environments Unit
 
How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17
 
Advantages and Disadvantages of CMS from an SEO Perspective
Advantages and Disadvantages of CMS from an SEO PerspectiveAdvantages and Disadvantages of CMS from an SEO Perspective
Advantages and Disadvantages of CMS from an SEO Perspective
 
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptxChapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
 
Operation Blue Star - Saka Neela Tara
Operation Blue Star   -  Saka Neela TaraOperation Blue Star   -  Saka Neela Tara
Operation Blue Star - Saka Neela Tara
 
Azure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHatAzure Interview Questions and Answers PDF By ScholarHat
Azure Interview Questions and Answers PDF By ScholarHat
 
CACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdfCACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdf
 
Francesca Gottschalk - How can education support child empowerment.pptx
Francesca Gottschalk - How can education support child empowerment.pptxFrancesca Gottschalk - How can education support child empowerment.pptx
Francesca Gottschalk - How can education support child empowerment.pptx
 
S1-Introduction-Biopesticides in ICM.pptx
S1-Introduction-Biopesticides in ICM.pptxS1-Introduction-Biopesticides in ICM.pptx
S1-Introduction-Biopesticides in ICM.pptx
 
How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...
 

Lec17 sparse signal processing & applications

  • 1. Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Lec 17 Sparse Signal Processing & Applications Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph: x 2346. http://l.web.umkc.edu/lizhu p.1Z. Li, Image Analysis & Retrv, 2016 Fall
  • 2. Outline  Recap:  Piece-wise Linear Models via Query Driven Solution  Subspace Indexing on Grassmann Manifold  Optimization of Subspace on Grassmann Manifold  Sparse Signal Processing  Sparse Representation and Robust PCA  Sparse Signal Processing  L1 norm and L1 Magic Solution  Application in occluded face recognition  Summary p.2Z. Li, Image Analysis & Retrv, 2016 Fall
  • 3. Piece-wise Linear : Query Driven • Query-Driven Piece-wise Linear Model – No pre-determined structure on the training data – Local neighborhood data patch identified from query point q, – Local model built with local data, A(X, q) p.3Z. Li, Image Analysis & Retrv, 2016 Fall
  • 4. DPC – Discriminant Power Coefficient  The tradeoffs in local data support size p.4Z. Li, Image Analysis & Retrv, 2016 Fall
  • 5. Face Recognition  On ATT Data set: 40 subjects, 400 images: Extra credit: 10pts   Develop a query driven local Laplacianface model for HW-3 p.5Z. Li, Image Analysis & Retrv, 2016 Fall
  • 6. Subspace Indexing on Grassmann Manifold • Subspace Clustering by Grassmann Metric: – It is a VQ like process. – Start with a data partition kd-tree, their leaf nodes and associated subspaces {Ak}, k=1..2h – Repeat » Find Ai and Aj, if darc(Ai, Aj) is the smallest among all, and the associated data patch are adjacent in the data space. » Delete Ai and Aj, replace with merged new subspace, and update associated data patch leaf nodes set. » Compute the empirical identification accuracy for the merged subspace » Add parent pointer to the merged new subspace for Ai and Aj . » Stop if only 1 subspace left. p.6Z. Li, Image Analysis & Retrv, 2016 Fall
  • 7. Simulation • Face data set – Mixed data set of 242 individuals, and 4840 face images – Performance compared with PCA, LDA and LPP modeling p.7Z. Li, Image Analysis & Retrv, 2016 Fall
  • 8. Newtonian Method in Optimization  Recall that in optimizing a functional over vector variables f(X), X in Rn, p.8 Credit: Kerstin Johnsson, Lund Univ Z. Li, Image Analysis & Retrv, 2016 Fall
  • 9. Gradient & Hessian on Grassmann Manifold  Gradient on Grassmann manifold: p.9Z. Li, Image Analysis & Retrv, 2016 Fall
  • 10. Hessian on Grassmann Manifold  Hessian:  FY = nxp 1st order differentiation  FYY= 2nd order differentiation along Y p.10Z. Li, Image Analysis & Retrv, 2016 Fall
  • 11. Newton’s Method on Grassmann Manifold  Overall framework Prof. A. Edelman’s matlab package:  https://umkc.box.com/s/g2oyqvsb2lx2v9wzf0ju60wnspts4t9g p.11Z. Li, Image Analysis & Retrv, 2016 Fall
  • 12. Outline  Recap:  Piece-wise Linear Models via Query Driven Solution  Subspace Indexing on Grassmann Manifold  Optimization of Subspace on Grassmann Manifold  Sparse Signal Processing  Sparse Representation and Robust PCA  Sparse Signal Processing  L1 norm and L1 Magic Solution  Application in occluded face recognition  Summary p.12Z. Li, Image Analysis & Retrv, 2016 Fall
  • 13. Sparse representation • Signals/Images are sparse if it can have very few non-zero coefficients representation in certain subspace: – E.g. cameraman image X represented as 2-D DCT in Y: • How is this related to classification problem ? – Intuitively, sparse is good for classification, because it is to separate samples from different classes – Only when data points are dense and intertwined , classification is hard – How to characterize this mathematically ?  x y=dct2(x) Eigen face p.13Z. Li, Image Analysis & Retrv, 2016 Fall
  • 14. Sparsity in Human Visual System p.14Z. Li, Image Analysis & Retrv, 2016 Fall
  • 15. Sparse Signal Recovery  If x is sparse, i.e |x|0 is small, we can recovery x by a random projection measurement, y=Ax  Basis pursuit de-noising:  LASSO: p.15Z. Li, Image Analysis & Retrv, 2016 Fall
  • 16. Sparse Face Model Consider a face recognition system  We have k=1,2,…,K subjects, each subject has nk training samples {[v1,1, .., v1,n1], [v2,1, .., v2,n2], …, [vK,1, .., vK,nK]}, each is a thumbnail image with d=wxh pixels.  Let us stack all training samples as a collection of column vectors, A, of d N, N=n1 + n2 + … + nK.  The problem is, for a given thumbnail image, y, with unknown class label, how to solve for its label ?K p.16Z. Li, Image Analysis & Retrv, 2016 Fall
  • 17. Assume y is belonging to class i, then, Or, Where only a small number of coefficients in x has non-zero entry, thus sparse. Sparsity p.17Z. Li, Image Analysis & Retrv, 2016 Fall
  • 18. Assume y is belonging to class 1, then, Most co-efficients related to other classes are zero, only a small number of non-zero coefficients in alpha 1 Illustration of Sparsity p.18Z. Li, Image Analysis & Retrv, 2016 Fall
  • 19. • So the problem is rather straight forward – Give y = Ax, where • y is the unknown face image in Rd, • A is the d x N training data matrix, or dictionary, with N large • x is the coefficients of y as linear combination of training samples that is sparse, out of total N coefficients, only a small number of them are non-zero – Mathematically, we are looking for : • Where |x|0 is L0 norm, which counts number of non-zero coefficients in x. Mathematical formulation 𝑥0 = arg min 𝑥 𝑥 0, 𝑠. 𝑡. , 𝐴𝑥 = 𝑦 p.19Z. Li, Image Analysis & Retrv, 2016 Fall
  • 20. • The L0 minimization problem is basically a combinatorial optimization problem • Not much structure to exploit fast algorithm • Dumbest solution: – Assuming that x has at most 3 non-zero coefficients, then search total – Possible coefficients combinations and find the one gives the best match – It is an kNN search in effect ! L0 minimization is NP hard 𝑁 1 + 𝑁 2 + 𝑁 3 p.20Z. Li, Image Analysis & Retrv, 2016 Fall
  • 21. L0 and L1 norm  Lk norm (recall minkowski distance) p.21Z. Li, Image Analysis & Retrv, 2016 Fall
  • 22. L1 solution L-2 ball p.22Z. Li, Image Analysis & Retrv, 2016 Fall
  • 23. L1 based recognition p.23Z. Li, Image Analysis & Retrv, 2016 Fall
  • 24. L1 solution for invalid input images • For non-face images: – Non sparse coefficients in x • Can threshold on residual to return not found result p.24Z. Li, Image Analysis & Retrv, 2016 Fall
  • 25. Occlusion and Disguise • A big problem in biometrics is disguise and occlusion • The magic of sparsity and L1 minimization can deal with that effectively ! • Consider a face image with a small fraction p of its pixels corrupted: p.25Z. Li, Image Analysis & Retrv, 2016 Fall
  • 26. • Let the occluded face images be y = Ax + e • Then re-state the constraint as, • then solve for P1 with y=Bw. Notice that sparsity in w is achieved thru sparsity in both x and e. Sparsity criteria takes care of occlusion p.26Z. Li, Image Analysis & Retrv, 2016 Fall
  • 27. • Occlusion example – Large L2 errors, not recoverable by Eigenface/Fisherface: • Accuracy for sunglasses and scarves effects: Occluded face recognition p.27Z. Li, Image Analysis & Retrv, 2016 Fall
  • 28. L1 vs L2 minimization • A natural question is why not solve y=Ax with L2 minimization ? – Typically, number of training samples is smaller than number of pixels in the training images, so why not do a pseudo-inverse like: – Which looks for a Maximum Likelihood estimation of true x, if noises are Gaussian with covariance sI. – However, the noises are non-gaussian and can be unbounded. The resulting L2 solution pretty bad p.28Z. Li, Image Analysis & Retrv, 2016 Fall
  • 29. L2 solution for Occlusion • Example with occlusion: – (a): Occluded face – (b): x solved from L2 minimization, not sparse at all – (c ): error – (d ): reconstruction from x p.29Z. Li, Image Analysis & Retrv, 2016 Fall
  • 30. L1 vs L2 minimization L1 vs L2 in 2D space: y=Ax p.30Z. Li, Image Analysis & Retrv, 2016 Fall
  • 31. Sparsity is bad news for L2 • Given training set A, the unknown image y is under- determined in A: – R(A): a set of y that satisfies y=Ax: p.31Z. Li, Image Analysis & Retrv, 2016 Fall
  • 32. Numeric solution for L1 minimization Candes (of CalTech)’s group has this L1 magic matlab toolbox  Check out manual on course webpage  Stephen Boyd:  Boyd’s nice book on Optimization can be downloaded from his webpage at Stanford.  Excellent book, with slides, homework and solutions.  https://web.stanford.edu/~boyd/cvxbook/bv_cvxbook.pdf p.32Z. Li, Image Analysis & Retrv, 2016 Fall
  • 33. Numerical Tool from L1 Magic  L1 Magic Toolbox: p.33 % signal length N = 512; % number of spikes in the signal, must be sparse w.r.t N T = 20; % number of observations to make K = 120; % random +/- 1 signal x = zeros(N,1); q = randperm(N); x(q(1:T)) = sign(randn(T,1)); subplot(3,1,1); plot(x); title('x(t)'); axis([1 500 -1.2 1.2]); % measurement matrix: random measuring fprintf('n Creating random measurement matrix...'); A = randn(K,N); % othorgonalize A = orth(A')'; % observations y = A*x; % initial guess = min energy x0 = A'*y; subplot(3,1,2); plot(x0); title('x_0(t)'); axis([1 500 -1.2 1.2]); % solve with primal-dual method xp = l1eq_pd(x0, A, [], y, 1e-3); subplot(3,1,3); plot(xp); title('x(t) recovered by L1 magic'); axis([1 500 -1.2 1.2]); % test l1magic end Z. Li, Image Analysis & Retrv, 2016 Fall
  • 34. L1 Magic demo 50 100 150 200 250 300 350 400 450 500 -1 0 1 x(t) 50 100 150 200 250 300 350 400 450 500 -1 0 1 x0(t) 50 100 150 200 250 300 350 400 450 500 -1 0 1 x(t) recovered by l1 magic Original sparse signal L1 magic recovered sparse signal Pseudo-inverse: L2 recovery p.34Z. Li, Image Analysis & Retrv, 2016 Fall
  • 35. Sparse face  Recover face as sparse signal p.35 % create our measure matrix A: face + nonface icons A=zeros(1600, w*h); A(1:400, :) = faces; A(401:1600, :) = nfaces; [N, dim]=size(A); % in col vec form A = A'; % pick a face: offs in 1-400 figure(3); colormap('gray'); offs = 20; y = faces(offs, :)'; subplot(2,2,1); axis off; imagesc(reshape(y, h,w)); title('fontsize{11}original'); % solve for xp = min |x|, s.t. y=Ax % initial guess = min energy x0 = A'*y; % solve with primal-dual method xp = l1eq_pd(x0, A, [], y, 1e-3); % normalize x0 = x0./norm(x0); xp = xp./norm(xp); % reconstructed face yp = A*xp; subplot(2,2,2); axis off; imagesc(reshape(yp, h,w)); title('fontsize{11}sparse reconstruction'); Z. Li, Image Analysis & Retrv, 2016 Fall
  • 36. L1Magic for Face Recognition p.36Z. Li, Image Analysis & Retrv, 2016 Fall
  • 37. Super Resolution Super-Resolution  Super-resolves a lower resolution patch, say k x k, to 3k x 3k.  Mathematically, learn a function: p.37 𝑓 𝑥 → 𝑌, 𝑥 ∈ 𝑅 𝑑, 𝑌 ∈ 𝑅 𝐷 Z. Li, Image Analysis & Retrv, 2016 Fall
  • 38. Basic Framework  Super-resolve is the inverse of down scaling:  Low res patch y is the blurred and scaled high res patch x:  Assume the high res image is sparse on some dictionary (true, say DCT): p.38 Output OriginalInput Training patches ≈ 𝑦 = 𝑆𝐻𝑥 Z. Li, Image Analysis & Retrv, 2016 Fall
  • 39. Coupled Dictionary Learning  Pre-train a common set of coupled low and high resolution dictionary  Super-resolve by solving L1 minimization on lower resolution patch, and use the same coeffiients to superresolve the higher resolution patch p.39Z. Li, Image Analysis & Retrv, 2016 Fall
  • 40. Coupled Dictionary Learning  Learn two sets of Dictionaries, Dh, Dl, that have common sparse coefficients for low and high resolution image patches, y and x:  Reconstruction of low res patch with sparse coefficients:  Furthermore, introduce a linear projection, F, to enforce perceptual metrics  Then the high res patch x, can be constructed as p.40 min 𝛼 0 , 𝑠. 𝑡. , 𝐷𝑙 𝛼 − 𝑦 2 ≤ 𝜖 min 𝛼 0 , 𝑠. 𝑡. , 𝐹𝐷𝑙 𝛼 − 𝐹𝑦 2 ≤ 𝜖 𝑥 = 𝐷ℎ 𝛼 Yang, J Wright, TS Huang, Y Ma, Image super-resolution via sparse representation, IEEE Trans. Image Processing, vol.19 (11), 2861-2873 Z. Li, Image Analysis & Retrv, 2016 Fall
  • 41. Coupled Dictionary Learning  Put together, super resolve is to solve:  Sparse reconstruction of lower resolution y  Enforce local consistence with high res patches, extract adjacent overlapping stripes, via P, to be in agreement, w is the previously reconstructed patch pixels:  Solution via Lagrangian relaxation: p.41Z. Li, Image Analysis & Retrv, 2016 Fall
  • 42. Overall Algorithm  Patch level super-resolution, complete with global image gradient search p.42Z. Li, Image Analysis & Retrv, 2016 Fall
  • 43. Dictionary Training Training data: low and high resolution image patches Yl={yk}, Xh={xk}:  Enforce the common sparse coefficients p.43Z. Li, Image Analysis & Retrv, 2016 Fall
  • 44. Results  Dictionary Training  From flowers and animals data set, covering a variety of texture  Training dictionary from more than 100,000 samples p.44 𝐷ℎ 𝐷𝑙 Z. Li, Image Analysis & Retrv, 2016 Fall
  • 45. Results  3x super-resolution p.45 Bicubic Neighbor embedding [Chang CVPR ‘04] Low-resolution input OriginalCoupled Dictionary Z. Li, Image Analysis & Retrv, 2016 Fall
  • 46. Related Work  Potential paper review project p.46Z. Li, Image Analysis & Retrv, 2016 Fall
  • 47. Summary  Sparse Signal Processing  If signal is sparse in some (unknown) domain, then from a random measurement, we can reliably recover the signal via L1 minimization  Applications: Robust PCA and Face Recognition with Occlusion  Face images are sparse linear combination from a face dictionary  Recovery from solving L1 problem ~ caveat: only additive noises can be delt.  Applications: Coupled Dictionary for Image Super Resolution  Coupled dictionary: high and low res image patches sharing the same coefficients. p.47 min 𝑥 𝑥 1, 𝑠. 𝑡. 𝑦 = 𝐴𝑥 Z. Li, Image Analysis & Retrv, 2016 Fall