SlideShare une entreprise Scribd logo
1  sur  34
Super-Resolution
Super-resolution
• convolutions, blur, and de-blurring
• Bayesian methods
• Wiener filtering and Markov Random Fields

• sampling, aliasing, and interpolation
• multiple (shifted) images
• prior-based methods
• MRFs
• learned models
• domain-specific models (faces)- Gary
3/7/2003

Super-Resolution

2
Linear systems
Basic properties
• homogeneity T[a X]
T[X1+X2]
• additivity

= a T[X]
= T[X1]+T[X2]

• superposition T[aX1+bX2] = aT[X1]+bT[X2]
Linear system ⇔ superposition
Examples:
• matrix operations (additions, multiplication)
• convolutions
3/7/2003

Super-Resolution

3
Signals and linear operators
Continuous
Discrete
Vector form

I(x)
I[k] or Ik
I

Discrete linear operator
y=Ax
Continuous linear operator:
convolution integral

g(x) = s h(ξ,x) f(ξ) dξ, h(ξ,x): impulse response
g(x) = s h(ξ-x) f(ξ) dξ= [f * h](x) shift invariant

3/7/2003

Super-Resolution

4
2-D signals and convolutions
Continuous
Discrete

I(x,y)
I[k,l] or Ik,l

2-D convolutions (discrete)
g[k,l] = ∑m,n f[m,n] h[k-m,l-n]
= ∑m,n f[m,n] h1[k-m]h2[l-n]

separable

Gaussian kernel is separable and radial
h(x,y) = (2πσ2)-1exp-(x2+y2)/σ2
3/7/2003

Super-Resolution

5
Convolution and blurring

3/7/2003

Super-Resolution

6
Separable binomial low-pass filter

3/7/2003

Super-Resolution

7
Fourier transforms
Project onto a series of complex sinusoids
F[m,n] = ∑k f[k,l] e-i 2π(km+ln)
Properties:
• shifting

g(x-x0) ⇔ exp(-i 2πfxx0)G(fx)

• differentiation dg(x)/dx ⇔ i 2πfxG(fx)
• convolution

3/7/2003

[f * g](x) ⇔ [F G] (fx)

Super-Resolution

8
Blurring examples
Increasing amounts of blur + Fourier transform

3/7/2003

Super-Resolution

9
Sharpening
Unsharp mask (darkroom photography):
• remove some low-frequency content
y’ = y + s (y – g * y)

spatial (blur, sharp)
3/7/2003

Super-Resolution

freq (blur,sharp)
10
Sharpening - result
Unsharp mask: original, blur (σ=1),
sharp(s=0, 1, 2)

3/7/2003

Super-Resolution

11
Deconvolution
Filter by inverse of blur
• easiest to do in the Fourier domain
• problem: high-frequency noise amplification

3/7/2003

Super-Resolution

12
Bayesian modeling
Use prior model for image and noise
• y = g * x + n, x is original, y is blurred
• p(x|y) = p(y|x)p(x)
= exp(-|y – g*x|2/2σn-2) exp(-|x|2/2σx-2)
• -log p(x|y) ∝ |y – g*x|2σn-2 + |x|2σx-2
where the norm || is summed squares over all
pixels
3/7/2003

Super-Resolution

13
Parseval’s Theorem
Energy equivalence in spatial ↔ frequency
domain
• |x|2 = |F(x)|2
• -log p(x|y) ∝ |Y(f) – G(f)X(f)|2σn-2 + |X(f)|2σx-2
• least squares solution (∂/∂X = 0)
X(f) = G(f)Y(f) / [G2(f) + σn2/σx2]

3/7/2003

Super-Resolution

14
Wiener filtering
Optimal linear filter given noise and signal
statistics
• X(f) = G(f)Y(f) / [G2(f) + σn2/σx2]
• low frequencies:
X(f) ≈ G-1(f)Y(f)
boost by inverse gain (blur)
X(f) ≈ G(f) σn-2σx2 Y(f)
• high frequencies:
attenuate by blur (gain)

3/7/2003

Super-Resolution

15
Wiener filtering – white noise prior
Assume all frequencies equally likely
• p(x) ~ N(0,σx2)
• X(f) = G(f)Y(f) / [G2(f) + σn2/σx2]
• solution is too noisy in high frequencies

3/7/2003

Super-Resolution

16
Wiener filtering – pink noise prior
Assume frequency falloff (“natural statistics”)
• p(X(f)) ~ N(0,|f|-βσx2)
• X(f) = G(f)Y(f) / [G2(f) + |f|βσn2/σx2]
• greater attenuation at high frequencies

G(f)
3/7/2003

H(f)
Super-Resolution

17
Markov Random Field modeling
Use spatial neighborhood prior for image
i
• -log p(x) = ∑ij∈Cρ(xi-xj)
where ρ(v) is a robust norm:

•
•
•
•

j

ρ(v) = v2: quadratic norm ↔ pink noise
ρ(v) = |v|: total variation (popular with maths)
ρ(v) = |v|β: natural statistics
ρ(v) = v2,|v|: Huber norm
[Schultz, R.R.; Stevenson, IEEE TIP, 1996]

3/7/2003

Super-Resolution

18
MRF estimation
Set up discrete energy (quadratic or non-)
• -log p(x|y) ∝ σn-2 |y – Gx|2 + ∑ij∈Cρ(xi-xj)
where G is sparse convolution matrix
• quadratic: solve sparse linear system
• non-quadratic: use sparse non-linear least
squares (Levenberg-Marquardt, gradient
descent, conjugate gradient, …)

3/7/2003

Super-Resolution

19
Sampling a signal
• sampling:
• creating a discrete signal from a continuous signal

• downsampling (decimation)
• subsampling a discrete signal

• upsampling
• introducing zeros between samples

• aliasing
• two sampled signals that differ in their original
form (many → one mapping)
3/7/2003

Super-Resolution

20
Sampling

interpolation

3/7/2003

Super-Resolution

21
Nyquist sampling theorem
Signal to be (down-) sampled must have a
bandwidth no larger than twice the sample
frequency

ωs = 2π / ns > 2 ω0

3/7/2003

Super-Resolution

22
Box filter (top hat)

3/7/2003

Super-Resolution

23
Ideal low-pass filter

3/7/2003

Super-Resolution

24
Simplified camera optics
1.
2.
3.
4.

Blur = pill-box*Bessel2 (diffr.) ≈ Gaussian
Integrate = box filter
Sample = produce single digital sample
Noise = additive white noise

3/7/2003

Super-Resolution

25
Aliasing
Aliasing (“jaggies” and “crawl”) is present if
blur amount < sampling (σ = 1)
• shift each image in previous pipeline by 1

3/7/2003

Super-Resolution

26
Aliasing - less
Less aliasing (“jaggies” and “crawl”) is present if
blur amount ~ sampling (σ = 2)
• shift each image in previous pipeline by 1

3/7/2003

Super-Resolution

27
Multi-image super-resolution
Exploit aliasing to recover frequencies above
Nyquist cutoff
∀ ∑kσn-2 |yk – Gkx|2 + ∑ij∈Cρ(xi-xj)
where Gk are sparse convolution matrices
• quadratic: solve sparse linear system
• non-quadratic: use sparse non-linear least
squares (Levenberg-Marquardt, gradient
descent, conjugate gradient, …)
• projection onto convex sets (POCS)
3/7/2003

Super-Resolution

28
Multi-image super-resolution
Need:
• accurate (sub-pixel) motion estimates
(Wednesday’s lecture)
• accurate models of blur (pre-filtering)
• accurate photometry
• no (or known) non-linear pre-processing
(Bayer mosaics)
• sufficient images and low-noise relative to
amount of aliasing
3/7/2003

Super-Resolution

29
Prior-based Super-Resolution
“Classical” non-Gaussian priors:
• robust or natural statistics
• maximum entropy (least blurry)
• constant colors (black & white images)

3/7/2003

Super-Resolution

30
Example-based Super-Resolution
William T. Freeman, Thouis R. Jones, and Egon C. Pasztor,
IEEE Computer Graphics and Applications, March/April, 2002

• learn the association between low-resolution
patches and high-resolution patches
• use Markov Network Model (another name for
Markov Random Field) to encourage adjacent
patch coherence

3/7/2003

Super-Resolution

31
Example-based Super-Resolution
William T. Freeman, Thouis R.
Jones, and Egon C.
Pasztor,
IEEE Computer Graphics
and Applications,
March/April, 2002

3/7/2003

Super-Resolution

32
References – “classic”
Irani, M. and Peleg. Improving Resolution by Image Registration. Graphical Models and Image
Processing, 53(3), May 1991, 231-239.
Schultz, R.R.; Stevenson, R.L. Extraction of high-resolution frames from video sequences. IEEE
Trans. Image Proc., 5(6), Jun 1996, 996-1011.
Elad, M.; Feuer, A.. Restoration of a single superresolution image from several blurred, noisy,
and undersampled measured images. IEEE Trans. Image Proc., 6(12) , Dec 1997, 16461658.
Elad, M.; Feuer, A.. Super-resolution reconstruction of image sequences. IEEE PAMI 21(9), Sep
1999, 817-834.
Capel, D.; Zisserman, A.. Super-resolution enhancement of text image sequences. CVPR 2000,
I-600-605 vol. 1.
Chaudhuri, S. (editor). Super-Resolution Imaging. Kluwer Academic Publishers. 2001.

3/7/2003

Super-Resolution

33
References – strong priors
Freeman, W.T.; Pasztor, E.C.. Learning low-level vision, CVPR 1999, 182-1189 vol.2
William T. Freeman, Thouis R. Jones, and Egon C. Pasztor, Example-based super-resolution,
IEEE Computer Graphics and Applications, March/April, 2002
Baker, S.; Kanade, T. Hallucinating faces. Automatic Face Gesture Recognition, 2000, 83-88.
Ce Liu; Heung-Yeung Shum; Chang-Shui Zhang. A two-step approach to hallucinating faces:
global parametric model and local nonparametric model. CVPR 2001. I-192-8.

08/03/2014

Super-Resolution

34

Contenu connexe

Tendances

06 spatial filtering DIP
06 spatial filtering DIP06 spatial filtering DIP
06 spatial filtering DIPbabak danyal
 
Lectures 1 3 final (4)
Lectures 1 3 final (4)Lectures 1 3 final (4)
Lectures 1 3 final (4)seemakashyap15
 
Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...
Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...
Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...IDES Editor
 
IMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAIN
IMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAINIMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAIN
IMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAINijma
 
03 digital image fundamentals DIP
03 digital image fundamentals DIP03 digital image fundamentals DIP
03 digital image fundamentals DIPbabak danyal
 
Adaptive Median Filters
Adaptive Median FiltersAdaptive Median Filters
Adaptive Median FiltersAmnaakhaan
 
Anatomy of a Texture Fetch
Anatomy of a Texture FetchAnatomy of a Texture Fetch
Anatomy of a Texture FetchMark Kilgard
 
Digital Image Processing: Image Restoration
Digital Image Processing: Image RestorationDigital Image Processing: Image Restoration
Digital Image Processing: Image RestorationMostafa G. M. Mostafa
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentationasodariyabhavesh
 
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...Norishige Fukushima
 
SPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSINGSPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSINGmuthu181188
 
Filtering an image is to apply a convolution
Filtering an image is to apply a convolutionFiltering an image is to apply a convolution
Filtering an image is to apply a convolutionAbhishek Mukherjee
 

Tendances (20)

06 spatial filtering DIP
06 spatial filtering DIP06 spatial filtering DIP
06 spatial filtering DIP
 
Ppt ---image processing
Ppt ---image processingPpt ---image processing
Ppt ---image processing
 
Lecture 7
Lecture 7Lecture 7
Lecture 7
 
Spatial domain and filtering
Spatial domain and filteringSpatial domain and filtering
Spatial domain and filtering
 
Lectures 1 3 final (4)
Lectures 1 3 final (4)Lectures 1 3 final (4)
Lectures 1 3 final (4)
 
Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...
Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...
Random Valued Impulse Noise Removal in Colour Images using Adaptive Threshold...
 
IMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAIN
IMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAINIMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAIN
IMAGE DENOISING BY MEDIAN FILTER IN WAVELET DOMAIN
 
Lecture 4
Lecture 4Lecture 4
Lecture 4
 
03 digital image fundamentals DIP
03 digital image fundamentals DIP03 digital image fundamentals DIP
03 digital image fundamentals DIP
 
Adaptive Median Filters
Adaptive Median FiltersAdaptive Median Filters
Adaptive Median Filters
 
Lecture 3
Lecture 3Lecture 3
Lecture 3
 
Anatomy of a Texture Fetch
Anatomy of a Texture FetchAnatomy of a Texture Fetch
Anatomy of a Texture Fetch
 
Digital Image Processing: Image Restoration
Digital Image Processing: Image RestorationDigital Image Processing: Image Restoration
Digital Image Processing: Image Restoration
 
Df4201720724
Df4201720724Df4201720724
Df4201720724
 
Spatial filtering
Spatial filteringSpatial filtering
Spatial filtering
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentation
 
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
 
SPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSINGSPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSING
 
Chapter 5
Chapter 5Chapter 5
Chapter 5
 
Filtering an image is to apply a convolution
Filtering an image is to apply a convolutionFiltering an image is to apply a convolution
Filtering an image is to apply a convolution
 

Similaire à Super Resolution in Digital Image processing

imageCorrectionLinearDiffusion
imageCorrectionLinearDiffusionimageCorrectionLinearDiffusion
imageCorrectionLinearDiffusionKellen Betts
 
Channel Models for Massive MIMO
Channel Models for Massive MIMOChannel Models for Massive MIMO
Channel Models for Massive MIMOCPqD
 
Wcsmo_presentation.pdf
Wcsmo_presentation.pdfWcsmo_presentation.pdf
Wcsmo_presentation.pdfZiaGondal1
 
Dynamics of structures with uncertainties
Dynamics of structures with uncertaintiesDynamics of structures with uncertainties
Dynamics of structures with uncertaintiesUniversity of Glasgow
 
Digital communication
Digital communicationDigital communication
Digital communicationmeashi
 
A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...
A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...
A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...mravendi
 
IVR - Chapter 5 - Bayesian methods
IVR - Chapter 5 - Bayesian methodsIVR - Chapter 5 - Bayesian methods
IVR - Chapter 5 - Bayesian methodsCharles Deledalle
 
Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...grssieee
 
IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb)
IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb) IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb)
IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb) Charles Deledalle
 
Course-Notes__Advanced-DSP.pdf
Course-Notes__Advanced-DSP.pdfCourse-Notes__Advanced-DSP.pdf
Course-Notes__Advanced-DSP.pdfShreeDevi42
 
Advanced_DSP_J_G_Proakis.pdf
Advanced_DSP_J_G_Proakis.pdfAdvanced_DSP_J_G_Proakis.pdf
Advanced_DSP_J_G_Proakis.pdfHariPrasad314745
 
slides-defense-jie
slides-defense-jieslides-defense-jie
slides-defense-jiejie ren
 

Similaire à Super Resolution in Digital Image processing (20)

imageCorrectionLinearDiffusion
imageCorrectionLinearDiffusionimageCorrectionLinearDiffusion
imageCorrectionLinearDiffusion
 
Image denoising
Image denoisingImage denoising
Image denoising
 
Lecture 6
Lecture 6Lecture 6
Lecture 6
 
Channel Models for Massive MIMO
Channel Models for Massive MIMOChannel Models for Massive MIMO
Channel Models for Massive MIMO
 
Wcsmo_presentation.pdf
Wcsmo_presentation.pdfWcsmo_presentation.pdf
Wcsmo_presentation.pdf
 
Deconvolution
DeconvolutionDeconvolution
Deconvolution
 
Tdm fdm
Tdm fdmTdm fdm
Tdm fdm
 
Dynamics of structures with uncertainties
Dynamics of structures with uncertaintiesDynamics of structures with uncertainties
Dynamics of structures with uncertainties
 
IARE_DSP_PPT.pptx
IARE_DSP_PPT.pptxIARE_DSP_PPT.pptx
IARE_DSP_PPT.pptx
 
Digital communication
Digital communicationDigital communication
Digital communication
 
A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...
A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...
A WIDEBAND SPECTRUM SENSING METHOD FOR COGNITIVE RADIO USING SUB-NYQUIST SAMP...
 
Fourier slide
Fourier slideFourier slide
Fourier slide
 
IVR - Chapter 5 - Bayesian methods
IVR - Chapter 5 - Bayesian methodsIVR - Chapter 5 - Bayesian methods
IVR - Chapter 5 - Bayesian methods
 
1519 differentiation-integration-02
1519 differentiation-integration-021519 differentiation-integration-02
1519 differentiation-integration-02
 
Extended Isolation Forest
Extended Isolation Forest Extended Isolation Forest
Extended Isolation Forest
 
Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...
 
IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb)
IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb) IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb)
IVR - Chapter 2 - Basics of filtering I: Spatial filters (25Mb)
 
Course-Notes__Advanced-DSP.pdf
Course-Notes__Advanced-DSP.pdfCourse-Notes__Advanced-DSP.pdf
Course-Notes__Advanced-DSP.pdf
 
Advanced_DSP_J_G_Proakis.pdf
Advanced_DSP_J_G_Proakis.pdfAdvanced_DSP_J_G_Proakis.pdf
Advanced_DSP_J_G_Proakis.pdf
 
slides-defense-jie
slides-defense-jieslides-defense-jie
slides-defense-jie
 

Plus de Ramrao Desai

Enhanced Data rates for Global Evolution (EDGE)
Enhanced Data rates for Global Evolution (EDGE)Enhanced Data rates for Global Evolution (EDGE)
Enhanced Data rates for Global Evolution (EDGE)Ramrao Desai
 
Relational model for Databases
Relational model for DatabasesRelational model for Databases
Relational model for DatabasesRamrao Desai
 
Java tutorial for Beginners and Entry Level
Java tutorial for Beginners and Entry LevelJava tutorial for Beginners and Entry Level
Java tutorial for Beginners and Entry LevelRamrao Desai
 
Using PowerPoint to Design Effective Presentations
Using PowerPoint to Design Effective PresentationsUsing PowerPoint to Design Effective Presentations
Using PowerPoint to Design Effective PresentationsRamrao Desai
 
Effective presentation for successful presentation
Effective presentation for successful presentationEffective presentation for successful presentation
Effective presentation for successful presentationRamrao Desai
 
Digital light processing
Digital light processingDigital light processing
Digital light processingRamrao Desai
 
Leading the way to an intelligent network
Leading the way to an intelligent networkLeading the way to an intelligent network
Leading the way to an intelligent networkRamrao Desai
 

Plus de Ramrao Desai (11)

Enhanced Data rates for Global Evolution (EDGE)
Enhanced Data rates for Global Evolution (EDGE)Enhanced Data rates for Global Evolution (EDGE)
Enhanced Data rates for Global Evolution (EDGE)
 
Relational model for Databases
Relational model for DatabasesRelational model for Databases
Relational model for Databases
 
Java tutorial for Beginners and Entry Level
Java tutorial for Beginners and Entry LevelJava tutorial for Beginners and Entry Level
Java tutorial for Beginners and Entry Level
 
Eerm mapping c++
Eerm mapping c++Eerm mapping c++
Eerm mapping c++
 
Using PowerPoint to Design Effective Presentations
Using PowerPoint to Design Effective PresentationsUsing PowerPoint to Design Effective Presentations
Using PowerPoint to Design Effective Presentations
 
Effective presentation for successful presentation
Effective presentation for successful presentationEffective presentation for successful presentation
Effective presentation for successful presentation
 
Internet Banking
Internet BankingInternet Banking
Internet Banking
 
Digital light processing
Digital light processingDigital light processing
Digital light processing
 
Capsule camera
Capsule cameraCapsule camera
Capsule camera
 
Cyber crime
Cyber crimeCyber crime
Cyber crime
 
Leading the way to an intelligent network
Leading the way to an intelligent networkLeading the way to an intelligent network
Leading the way to an intelligent network
 

Dernier

Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpinRaunakKeshri1
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...Pooja Nehwal
 
JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...
JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...
JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...anjaliyadav012327
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
9548086042 for call girls in Indira Nagar with room service
9548086042  for call girls in Indira Nagar  with room service9548086042  for call girls in Indira Nagar  with room service
9548086042 for call girls in Indira Nagar with room servicediscovermytutordmt
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesFatimaKhan178732
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdfSoniaTolstoy
 
Disha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdfDisha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdfchloefrazer622
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
The byproduct of sericulture in different industries.pptx
The byproduct of sericulture in different industries.pptxThe byproduct of sericulture in different industries.pptx
The byproduct of sericulture in different industries.pptxShobhayan Kirtania
 

Dernier (20)

Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...
 
JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...
JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...
JAPAN: ORGANISATION OF PMDA, PHARMACEUTICAL LAWS & REGULATIONS, TYPES OF REGI...
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
9548086042 for call girls in Indira Nagar with room service
9548086042  for call girls in Indira Nagar  with room service9548086042  for call girls in Indira Nagar  with room service
9548086042 for call girls in Indira Nagar with room service
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and Actinides
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
 
Disha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdfDisha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdf
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
The byproduct of sericulture in different industries.pptx
The byproduct of sericulture in different industries.pptxThe byproduct of sericulture in different industries.pptx
The byproduct of sericulture in different industries.pptx
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 

Super Resolution in Digital Image processing

  • 2. Super-resolution • convolutions, blur, and de-blurring • Bayesian methods • Wiener filtering and Markov Random Fields • sampling, aliasing, and interpolation • multiple (shifted) images • prior-based methods • MRFs • learned models • domain-specific models (faces)- Gary 3/7/2003 Super-Resolution 2
  • 3. Linear systems Basic properties • homogeneity T[a X] T[X1+X2] • additivity = a T[X] = T[X1]+T[X2] • superposition T[aX1+bX2] = aT[X1]+bT[X2] Linear system ⇔ superposition Examples: • matrix operations (additions, multiplication) • convolutions 3/7/2003 Super-Resolution 3
  • 4. Signals and linear operators Continuous Discrete Vector form I(x) I[k] or Ik I Discrete linear operator y=Ax Continuous linear operator: convolution integral g(x) = s h(ξ,x) f(ξ) dξ, h(ξ,x): impulse response g(x) = s h(ξ-x) f(ξ) dξ= [f * h](x) shift invariant 3/7/2003 Super-Resolution 4
  • 5. 2-D signals and convolutions Continuous Discrete I(x,y) I[k,l] or Ik,l 2-D convolutions (discrete) g[k,l] = ∑m,n f[m,n] h[k-m,l-n] = ∑m,n f[m,n] h1[k-m]h2[l-n] separable Gaussian kernel is separable and radial h(x,y) = (2πσ2)-1exp-(x2+y2)/σ2 3/7/2003 Super-Resolution 5
  • 7. Separable binomial low-pass filter 3/7/2003 Super-Resolution 7
  • 8. Fourier transforms Project onto a series of complex sinusoids F[m,n] = ∑k f[k,l] e-i 2π(km+ln) Properties: • shifting g(x-x0) ⇔ exp(-i 2πfxx0)G(fx) • differentiation dg(x)/dx ⇔ i 2πfxG(fx) • convolution 3/7/2003 [f * g](x) ⇔ [F G] (fx) Super-Resolution 8
  • 9. Blurring examples Increasing amounts of blur + Fourier transform 3/7/2003 Super-Resolution 9
  • 10. Sharpening Unsharp mask (darkroom photography): • remove some low-frequency content y’ = y + s (y – g * y) spatial (blur, sharp) 3/7/2003 Super-Resolution freq (blur,sharp) 10
  • 11. Sharpening - result Unsharp mask: original, blur (σ=1), sharp(s=0, 1, 2) 3/7/2003 Super-Resolution 11
  • 12. Deconvolution Filter by inverse of blur • easiest to do in the Fourier domain • problem: high-frequency noise amplification 3/7/2003 Super-Resolution 12
  • 13. Bayesian modeling Use prior model for image and noise • y = g * x + n, x is original, y is blurred • p(x|y) = p(y|x)p(x) = exp(-|y – g*x|2/2σn-2) exp(-|x|2/2σx-2) • -log p(x|y) ∝ |y – g*x|2σn-2 + |x|2σx-2 where the norm || is summed squares over all pixels 3/7/2003 Super-Resolution 13
  • 14. Parseval’s Theorem Energy equivalence in spatial ↔ frequency domain • |x|2 = |F(x)|2 • -log p(x|y) ∝ |Y(f) – G(f)X(f)|2σn-2 + |X(f)|2σx-2 • least squares solution (∂/∂X = 0) X(f) = G(f)Y(f) / [G2(f) + σn2/σx2] 3/7/2003 Super-Resolution 14
  • 15. Wiener filtering Optimal linear filter given noise and signal statistics • X(f) = G(f)Y(f) / [G2(f) + σn2/σx2] • low frequencies: X(f) ≈ G-1(f)Y(f) boost by inverse gain (blur) X(f) ≈ G(f) σn-2σx2 Y(f) • high frequencies: attenuate by blur (gain) 3/7/2003 Super-Resolution 15
  • 16. Wiener filtering – white noise prior Assume all frequencies equally likely • p(x) ~ N(0,σx2) • X(f) = G(f)Y(f) / [G2(f) + σn2/σx2] • solution is too noisy in high frequencies 3/7/2003 Super-Resolution 16
  • 17. Wiener filtering – pink noise prior Assume frequency falloff (“natural statistics”) • p(X(f)) ~ N(0,|f|-βσx2) • X(f) = G(f)Y(f) / [G2(f) + |f|βσn2/σx2] • greater attenuation at high frequencies G(f) 3/7/2003 H(f) Super-Resolution 17
  • 18. Markov Random Field modeling Use spatial neighborhood prior for image i • -log p(x) = ∑ij∈Cρ(xi-xj) where ρ(v) is a robust norm: • • • • j ρ(v) = v2: quadratic norm ↔ pink noise ρ(v) = |v|: total variation (popular with maths) ρ(v) = |v|β: natural statistics ρ(v) = v2,|v|: Huber norm [Schultz, R.R.; Stevenson, IEEE TIP, 1996] 3/7/2003 Super-Resolution 18
  • 19. MRF estimation Set up discrete energy (quadratic or non-) • -log p(x|y) ∝ σn-2 |y – Gx|2 + ∑ij∈Cρ(xi-xj) where G is sparse convolution matrix • quadratic: solve sparse linear system • non-quadratic: use sparse non-linear least squares (Levenberg-Marquardt, gradient descent, conjugate gradient, …) 3/7/2003 Super-Resolution 19
  • 20. Sampling a signal • sampling: • creating a discrete signal from a continuous signal • downsampling (decimation) • subsampling a discrete signal • upsampling • introducing zeros between samples • aliasing • two sampled signals that differ in their original form (many → one mapping) 3/7/2003 Super-Resolution 20
  • 22. Nyquist sampling theorem Signal to be (down-) sampled must have a bandwidth no larger than twice the sample frequency ωs = 2π / ns > 2 ω0 3/7/2003 Super-Resolution 22
  • 23. Box filter (top hat) 3/7/2003 Super-Resolution 23
  • 25. Simplified camera optics 1. 2. 3. 4. Blur = pill-box*Bessel2 (diffr.) ≈ Gaussian Integrate = box filter Sample = produce single digital sample Noise = additive white noise 3/7/2003 Super-Resolution 25
  • 26. Aliasing Aliasing (“jaggies” and “crawl”) is present if blur amount < sampling (σ = 1) • shift each image in previous pipeline by 1 3/7/2003 Super-Resolution 26
  • 27. Aliasing - less Less aliasing (“jaggies” and “crawl”) is present if blur amount ~ sampling (σ = 2) • shift each image in previous pipeline by 1 3/7/2003 Super-Resolution 27
  • 28. Multi-image super-resolution Exploit aliasing to recover frequencies above Nyquist cutoff ∀ ∑kσn-2 |yk – Gkx|2 + ∑ij∈Cρ(xi-xj) where Gk are sparse convolution matrices • quadratic: solve sparse linear system • non-quadratic: use sparse non-linear least squares (Levenberg-Marquardt, gradient descent, conjugate gradient, …) • projection onto convex sets (POCS) 3/7/2003 Super-Resolution 28
  • 29. Multi-image super-resolution Need: • accurate (sub-pixel) motion estimates (Wednesday’s lecture) • accurate models of blur (pre-filtering) • accurate photometry • no (or known) non-linear pre-processing (Bayer mosaics) • sufficient images and low-noise relative to amount of aliasing 3/7/2003 Super-Resolution 29
  • 30. Prior-based Super-Resolution “Classical” non-Gaussian priors: • robust or natural statistics • maximum entropy (least blurry) • constant colors (black & white images) 3/7/2003 Super-Resolution 30
  • 31. Example-based Super-Resolution William T. Freeman, Thouis R. Jones, and Egon C. Pasztor, IEEE Computer Graphics and Applications, March/April, 2002 • learn the association between low-resolution patches and high-resolution patches • use Markov Network Model (another name for Markov Random Field) to encourage adjacent patch coherence 3/7/2003 Super-Resolution 31
  • 32. Example-based Super-Resolution William T. Freeman, Thouis R. Jones, and Egon C. Pasztor, IEEE Computer Graphics and Applications, March/April, 2002 3/7/2003 Super-Resolution 32
  • 33. References – “classic” Irani, M. and Peleg. Improving Resolution by Image Registration. Graphical Models and Image Processing, 53(3), May 1991, 231-239. Schultz, R.R.; Stevenson, R.L. Extraction of high-resolution frames from video sequences. IEEE Trans. Image Proc., 5(6), Jun 1996, 996-1011. Elad, M.; Feuer, A.. Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images. IEEE Trans. Image Proc., 6(12) , Dec 1997, 16461658. Elad, M.; Feuer, A.. Super-resolution reconstruction of image sequences. IEEE PAMI 21(9), Sep 1999, 817-834. Capel, D.; Zisserman, A.. Super-resolution enhancement of text image sequences. CVPR 2000, I-600-605 vol. 1. Chaudhuri, S. (editor). Super-Resolution Imaging. Kluwer Academic Publishers. 2001. 3/7/2003 Super-Resolution 33
  • 34. References – strong priors Freeman, W.T.; Pasztor, E.C.. Learning low-level vision, CVPR 1999, 182-1189 vol.2 William T. Freeman, Thouis R. Jones, and Egon C. Pasztor, Example-based super-resolution, IEEE Computer Graphics and Applications, March/April, 2002 Baker, S.; Kanade, T. Hallucinating faces. Automatic Face Gesture Recognition, 2000, 83-88. Ce Liu; Heung-Yeung Shum; Chang-Shui Zhang. A two-step approach to hallucinating faces: global parametric model and local nonparametric model. CVPR 2001. I-192-8. 08/03/2014 Super-Resolution 34