Image Restoration – Degradation Model and General Approaches

Slides:



Advertisements
Similar presentations
2007Theo Schouten1 Restoration With Image Restoration one tries to repair errors or distortions in an image, caused during the image creation process.
Advertisements

ECE 472/572 - Digital Image Processing Lecture 7 - Image Restoration - Noise Models 10/04/11.
Digital Image Processing Lecture 11: Image Restoration Prof. Charlene Tsai.
Digital Image Processing Chapter 5: Image Restoration.
Digital Image Processing
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 5 Image Restoration Chapter 5 Image Restoration.
Image Restoration 影像復原 Spring 2005, Jen-Chang Liu.
DIGITAL IMAGE PROCESSING
5. 1 Model of Image degradation and restoration
ECE 472/572 - Digital Image Processing Lecture 8 - Image Restoration – Linear, Position-Invariant Degradations 10/10/11.
Digital Image Processing: Revision
Digital Image Processing
Digital Image Processing Chapter 5: Image Restoration.
DIGITAL IMAGE PROCESSING Instructors: Dr J. Shanbehzadeh M.Gholizadeh M.Gholizadeh
Chapter 5 Image Restoration. Preview Goal: improve an image in some predefined sense. Image enhancement: subjective process Image restoration: objective.
Digital Image Processing Lecture 4 Image Restoration and Reconstruction Second Semester Azad University Islamshar Branch
© by Yu Hen Hu 1 ECE533 Digital Image Processing Image Restoration.
Chapter 5 Image Restoration.
Image Restoration and Reconstruction (Noise Removal)
Computer Vision - Restoration Hanyang University Jong-Il Park.
DIGITAL IMAGE PROCESSING Instructors: Dr J. Shanbehzadeh M.Gholizadeh M.Gholizadeh
EE4328, Section 005 Introduction to Digital Image Processing Linear Image Restoration Zhou Wang Dept. of Electrical Engineering The Univ. of Texas.
Deconvolution, Deblurring and Restoration T , Biomedical Image Analysis Seminar Presentation Seppo Mattila & Mika Pollari.
Digital Image Processing
Chapter 3: Image Restoration Introduction. Image restoration methods are used to improve the appearance of an image by applying a restoration process.
CS654: Digital Image Analysis
انجمن دانشجویان ایران – مرجع دانلود کتاب ، نمونه سوال و جزوات درسی
IMAGE RESTORATION Outline A model of the image degradation / restoration process Noise models Restoration in the presence of noise only – spatial filtering.
Image Restoration Chapter 5.
CS654: Digital Image Analysis Lecture 22: Image Restoration - II.
Digital Image Processing Lecture 10: Image Restoration March 28, 2005 Prof. Charlene Tsai.
Image Restoration.
Digital Image Processing Lecture : Image Restoration
Image Restoration Fasih ur Rehman. –Goal of restoration: improve image quality –Is an objective process compared to image enhancement –Restoration attempts.
Digital Image Processing Lecture 10: Image Restoration
8-1 Chapter 8: Image Restoration Image enhancement: Overlook degradation processes, deal with images intuitively Image restoration: Known degradation processes;
Ch5 Image Restoration CS446 Instructor: Nada ALZaben.
Lecture 10 Image restoration and reconstruction 1.Basic concepts about image degradation/restoration 2.Noise models 3.Spatial filter techniques for restoration.
Digital Image Processing Lecture 11: Image Restoration March 30, 2005 Prof. Charlene Tsai.
Chapter 5 Image Restoration.
By Dr. Rajeev Srivastava
Image Restoration: Noise Models By Dr. Rajeev Srivastava.
CS654: Digital Image Analysis Lecture 22: Image Restoration.
Image Restoration. Image restoration vs. image enhancement Enhancement:  largely a subjective process  Priori knowledge about the degradation is not.
Lecture 22 Image Restoration. Image restoration Image restoration is the process of recovering the original scene from the observed scene which is degraded.
6/10/20161 Digital Image Processing Lecture 09: Image Restoration-I Naveed Ejaz.
Lecture 10 Chapter 5: Image Restoration. Image restoration Image restoration is the process of recovering the original scene from the observed scene which.
Digital Image Processing
Digital Image Processing Lecture 10: Image Restoration
IMAGE PROCESSING IMAGE RESTORATION AND NOISE REDUCTION
Degradation/Restoration Model
Image Restoration Spring 2005, Jen-Chang Liu.
Digital Image Processing
Business Statistics Topic 5
Digital Image Processing
DIGITAL IMAGE PROCESSING
IMAGE RESTORATION.
The Chinese University of Hong Kong
Lecture 11 Image restoration and reconstruction II
Image Analysis Image Restoration.
- photometric aspects of image formation gray level images
Outline Linear Shift-invariant system Linear filters
Image Restoration and Denoising
ENG4BF3 Medical Image Processing
Image Restoration - Focus on Noise
Digital Image Processing Week IV
Lecture 14 Figures from Gonzalez and Woods, Digital Image Processing, Second Edition, 2002.
Digital Image Processing
Digital Image Processing Lecture 11: Image Restoration
Presentation transcript:

Image Restoration – Degradation Model and General Approaches

Image enhancement vs. restoration Degradation model Image Restoration - 1 Outline Image enhancement vs. restoration Degradation model Noise only Linear, space-invariant General approaches Inverse filters Wiener filters Constrained least squares filtering

Image Restoration - 1 Image enhancement vs. restoration Image enhancement : process image so that the result is more suitable for a specific application, is largely a subjective process. Image restoration : recover image from distortions to its original image, is largely an objective process.

Apply the inverse process to recover the original image Image Restoration - 1 General approaches Model the degradation Apply the inverse process to recover the original image The degradation process is modeled as a degradation function with an additive noise term.

Degradation models : noise only Image Restoration - 1 Degradation models : noise only Noise models Spatial characteristics (independent or dependent) Intensity ( distribution, spectrum) Uniform, Gaussian, Rayleigh, Gamma (Erlang), Exponential, impulse Correlation with the image (additive, multiplicative) De-noising Spatial filtering Frequency domain filtering The principal sources of noise arise during image acquisition and/or transmission.

Image Restoration - 1 Noise models – examples

Image Restoration - 1 Noise models – examples

Degradation models : noise only Image Restoration - 1 Degradation models : noise only Noise simulation (Random number/signal generator) 盛文,焦晓丽. 雷达系统建模与仿真导论. 国防工业出版社,2006 The principal sources of noise arise during image acquisition and/or transmission.

Degradation models : noise only Image Restoration - 1 Degradation models : noise only 高斯分布随机变量的近似产生方法 中心极限定理:n个均值为 、方差为 的随机变量的和服从均值为 、方差为 的近似正态分布 取n个[0,1]区间上的均匀分布随机变量,则以下随机变量服从均值为0、方差为1的近似标准正态分布。

Image Restoration - 1 Noise models – periodic noise

Estimation of noise parameters Image Restoration - 1 De-noising Estimation of noise parameters By spectrum inspection: for periodic noise By test image: mean, variance and histogram shape, if imaging system is available By small patches, if only image is available De-noising Spatial filtering ( for additive noise) Mean filters Order-statistics filters Adaptive filters Frequency domain filtering (for periodic noise)

De-noising – Gaussian noise example Image Restoration - 1 De-noising – Gaussian noise example Arithmetic mean filter Geometric mean filter

Order-statistics filters Image Restoration - 1 De-noising Order-statistics filters Median filter Good for impulse noise reduction with less blurring Max filter Find the brightest points Min filter Find the darkest points Midpoint filter Combines order statistics and averaging, works best for randomly distributed noise.

Image Restoration - 1 De-noising – Salt & Pepper noise example

Image Restoration - 1 De-noising – Salt & Pepper noise example

De-noising – Adaptive filters Image Restoration - 1 De-noising – Adaptive filters Adaptive local noise reduction filter Adaptive median filter Homework: read pp.241-243

Image Restoration - 1 De-noising – Adaptive local filter

Image Restoration - 1 De-noising – Periodic noise example

Image Restoration - 1 De-noising – evaluation PSNR Visual perception

De-noising – evaluation example Image Restoration - 1 De-noising – evaluation example ImageDenoising.m

Degradation models: linear vs. non-linear Image Restoration - 1 Degradation models: linear vs. non-linear Many types of degradation can be approximated by linear, space invariant processes Can take advantages of the mature techniques developed for linear systems Non-linear and space variant models are more accurate Difficult to solve Unsolvable

Linear, space-invariant degradations Image Restoration - 1 Linear, space-invariant degradations Sampling theorem --> Linearity, additivity --> Linearity, homogeneity --> Space-invariant --> (convolution integral)

Image Restoration - 1 Linear, space-invariant degradations (cont’) Point Spread Function: Linear, space-invariant degradation model:

Estimating degradation function - 1 Image Restoration - 1 Estimating degradation function - 1 Estimation by image observation Degradation system H is completely characterized by its impulse response Select a small section from the degraded image Reconstruct an unblurred image of the same size The degradation function can be estimated by By ignoring the noise term, G(u,v) = F(u,v)H(u,v). If F(u,v) is the Fourier transform of point source (impulse), then G(u,v) is approximates H(u,v).

Estimating degradation function - 2 Image Restoration - 1 Estimating degradation function - 2 Estimation by experimentation Point spread function (PSF) Used in optics The impulse becomes a point of light The impulse response is commonly referred to as the PSF

Image Restoration - 1 Estimating degradation function - 3 Estimation by modeling – atmospheric turbulence

Image Restoration - 1 Estimating degradation function - 3 Estimation by modeling – linear motion blurring

The regularization theory Image Restoration - 1 Different approaches Classical approaches Inverse filter Weiner filter Algebraic approaches The regularization theory

Image Restoration - 1 Inverse filtering Degradation model This expression tells us that even if we know the degradation function we cannot recover the undegraded image exactly because of the random noise, whose Fourier transform is not known. Image restoration is an ill-posed problem. When H(u,v) is very small, the noise term dominates the restoration result.

Inverse filtering - examples Image Restoration - 1 Inverse filtering - examples This expression tells us that even if we know the degradation function we cannot recover the undegraded image exactly because of the random noise, whose Fourier transform is not known. Image restoration is an ill-posed problem. When H(u,v) is very small, the noise term dominates the restoration result.

Image Restoration - 1 Wiener filtering In most images, adjacent pixels are highly correlated, while the gray level of widely separated pixels are only loosely correlated. Therefore, the autocorrelation function of typical images generally decreases away from the origin. Power spectrum of an image is the Fourier transform of its autocorrelation function, therefore we can argue that the power spectrum of an image generally decreases with frequency. Typical noise sources have either a flat power spectrum or one that decreases with frequency more slowly than typical image power spectrum. Therefore, the expected situation is for the signal to dominate the spectrum at low frequencies, while the noise dominates the high frequencies.

Image Restoration - 1 Wiener filtering (cont’) Degradation model Wiener filter

Image Restoration - 1 Wiener filtering - example

Image Restoration - 1 Wiener filtering - example

Image Restoration - 1 Wiener filtering - problems The power spectra of the undegraded image and noise must be known. Weights all errors equally regardless of their location in the image, while the eye is considerably more tolerant of errors in the dark areas and high-gradient areas in the image. In minimizing the mean square error, Wiener filter also smooth the image more than the eye would prefer.

Image Restoration - 1 Constrained Least Squares Filtering Only the mean and variance of the noise is required The degradation model in vector-matrix form The objective function

Image Restoration - 1 Constrained Least Squares Filtering The solution

Image Restoration - 1 Constrained Least Squares Filtering - example