Download presentation
Presentation is loading. Please wait.
Published byJonathan Carr Modified over 9 years ago
1
Computer Vision - Restoration Hanyang University Jong-Il Park
2
Department of Computer Science and Engineering, Hanyang University Restoration vs. Enhancement Restoration Objective process A priori knowledge on degradation model Modeling the degradation and applying the inverse process to recover the original To improve an image in some predefined sense Enhancement Subjective process
3
Department of Computer Science and Engineering, Hanyang University Restoration process
4
Department of Computer Science and Engineering, Hanyang University Noise models Assume noise is independent of spatial coordinates and it is uncorrelated w.r.t. the image. Gaussian: electronic circuit noise, sensor noise Rayleigh: range images Exponential and gamma: laser images impulse(salt-and-pepper): faulty switching
5
Department of Computer Science and Engineering, Hanyang University Eg. Sample noisy images
6
Department of Computer Science and Engineering, Hanyang University Eg. Sample noisy images(cont.)
7
Department of Computer Science and Engineering, Hanyang University Periodic noise Spatially dependent noise Periodic noise can be reduced significantly via frequency domain filtering
8
Department of Computer Science and Engineering, Hanyang University Estimation of noise parameters PDF from small patches
9
Department of Computer Science and Engineering, Hanyang University When the only degradation is noise Periodic noise subtraction gives a good result Random noise mean filter, order-statistics filter,…
10
Department of Computer Science and Engineering, Hanyang University Mean filters Arithmetic mean filters For Gaussian or uniform noise Geometric mean filters For Gaussian or uniform noise Harmonic mean filters Work well for salt noise but fail for pepper noise Contraharmonic mean filters Suited for impulse noise but require identification(salt or pepper)
11
Department of Computer Science and Engineering, Hanyang University Arithmetic & Geometric mean filter
12
Department of Computer Science and Engineering, Hanyang University Contraharmonic filters Q<0 : eliminates salt noise Q=-1 harmonic mean filter Q=0 : arithmetic mean filter Q>0: eliminates pepper noise
13
Department of Computer Science and Engineering, Hanyang University Eg. Contraharmonic filters
14
Department of Computer Science and Engineering, Hanyang University Wrong sign in contraharmonic filters Disaster!
15
Department of Computer Science and Engineering, Hanyang University Order-Statistics filters Median filter Max filter Min filter Midpoint filter Alpha-trimmed mean filter
16
Department of Computer Science and Engineering, Hanyang University Median filters 3x3 median median median blurred
17
Department of Computer Science and Engineering, Hanyang University Max and Min filter Max filter Min filter Removes pepper noise Removes dark pixels Removes salt noise Removes light pixels Makes dark objects larger
18
Department of Computer Science and Engineering, Hanyang University Eg. Comparison (a) Additive uniform noise (b) (a)+additive S&P 5x5 arithmetic mean 5x5 geometric mean 5x5 median5x5 alpha-trimmed Mean(d=5)
19
Department of Computer Science and Engineering, Hanyang University Adaptive filters Behavior changes locally based on statistical characteristics of local support Simple adaptive filter based on mean and variance 1. If global_var is zero, then f(x,y)=g(x,y) 2. If local_var>global_var, then f(x,y)=g(x,y) (high local var edge should be preserved) 3. If local_var==global_var, then arithmetic mean filtering
20
Department of Computer Science and Engineering, Hanyang University Eg. Adaptive filter
21
Department of Computer Science and Engineering, Hanyang University Adaptive median filter Cope with impulse noise with large probability Preserve detail while smoothing non-impulse noise Level A:A1=z med -z min A2=z med -z max If A1>0 AND A2<0, go to level B Else increase the window size If window size<=S max repeat level A Else output z xy Level B:B1=z xy -z min B2=z xy -z max If B1>0 AND B2<0, output z xy Else output z med Algorithm
22
Department of Computer Science and Engineering, Hanyang University Eg. Adaptive median filter medianadaptive median
23
Department of Computer Science and Engineering, Hanyang University Periodic noise reduction By frequency domain filtering Band reject filter
24
Department of Computer Science and Engineering, Hanyang University Eg. Periodic noise reduction
25
Department of Computer Science and Engineering, Hanyang University Noise extraction By bandpass filter Help understanding noise pattern
26
Department of Computer Science and Engineering, Hanyang University Notch filters
27
Department of Computer Science and Engineering, Hanyang University Eg. Notch filtering Removing sensor scan- line patterns
28
Department of Computer Science and Engineering, Hanyang University Optimum notch filtering First isolating the principal contributions of the interference pattern Then subtracting weighted portion of the pattern from the corrupted image
29
Department of Computer Science and Engineering, Hanyang University Eg. Periodic interference(1/3) Noisy image
30
Department of Computer Science and Engineering, Hanyang University Eg. Periodic interference(2/3) Extraction of noise interference pattern
31
Department of Computer Science and Engineering, Hanyang University Eg. Periodic interference(3/3) Restored image by subtracting weighted portion of periodic interference (Refer to the derivation of weights in pp.250-252)
32
Department of Computer Science and Engineering, Hanyang University Linear, Position-Invariant Degradation
33
Department of Computer Science and Engineering, Hanyang University Degradation knowledge Degradation knowledge about 1. A priori (known) 2. A posteriori (unknown) blind restoration or blind deconvolution Restoration: determine the original image, given the observed image and knowledge about the degradation (H).
34
Department of Computer Science and Engineering, Hanyang University Fundamental issue Restoration problem restoration is to find, such that but, 1. does not exist: singular 2. may exist, but not be unique: ill-conditioned 3. may exist and unique, but there exists, which can be made arbitrarily small, such that which is not negligible Image restoration is ill-conditioned at best and Image restoration is ill-conditioned at best and singular at worst singular at worst
35
Department of Computer Science and Engineering, Hanyang University Estimation of degradation function Approaches Observation Experimentation Mathematical modeling
36
Department of Computer Science and Engineering, Hanyang University Estimation by observation Looking at a small section of the image containing simple structures and then obtaining degradation function Observed sub-image: Estimate of original image:
37
Department of Computer Science and Engineering, Hanyang University Estimation by experimentation Possible only if equipment similar to the equipment used to acquire the degraded images is available Eg. Use an impulse
38
Department of Computer Science and Engineering, Hanyang University Estimation by modeling Based on either physical characteristics or basic principles Eg.1. Physical characteristics: atmospheric turbulence Eg.2. Math derivation: motion blur Starting from After some manipulation(p.259) Setting the motion model, we obtain the degradation func.
39
Department of Computer Science and Engineering, Hanyang University Eg.1. Physical model Atmospheric turbulence
40
Department of Computer Science and Engineering, Hanyang University Eg.2. Math modeling Motion blur
41
Department of Computer Science and Engineering, Hanyang University Restoration methods Inverse filtering Wiener filtering Constrained least square filtering Geometric mean filtering Etc..
42
Department of Computer Science and Engineering, Hanyang University Inverse filtering Poor performance! Very sensitive to noise Noise amplification when H(u,v) is small
43
Department of Computer Science and Engineering, Hanyang University Eg. Inverse filtering
44
Department of Computer Science and Engineering, Hanyang University Minimum mean-square error filter Necessary to handle noise explicitly Statistical characteristics of noise should be incorporated into the restoration process MMSE filter To find an estimate of the uncorrupted image such that the mean square error between them is minimized: Assume: the noise and the image are uncorrelated The one or the other has zero mean The gray levels in the estimate are a linear function of the levels in the degraded image Derivation: Homework
45
Department of Computer Science and Engineering, Hanyang University MMSE filter (cont.) Frequency domain expression: Approximation of the Wiener filter Wiener filter PS of noisePS of image f
46
Department of Computer Science and Engineering, Hanyang University Eg. Wiener filtering Using the approximation K is chosen interactively
47
Department of Computer Science and Engineering, Hanyang University Eg. Restoration by Wiener filter motion blur Severe noise Moderate noise Negligible noise
48
Department of Computer Science and Engineering, Hanyang University Constrained Least Square Filtering Difficulty in Wiener filter The power spectra of the undegraded image and noise must be known Minimization in a statistical sense The constrained LS filtering requires knowledge of Mean of the noise Variance of the noise Optimal result for each image
49
Department of Computer Science and Engineering, Hanyang University Vector-matrix form of convolution g: MN-vector (lexicographical order of an image) f: MN-vector H: MNxMN matrix
50
Department of Computer Science and Engineering, Hanyang University Formulation: Constrained LS filter To find the minimum of a criterion function C defined as subject to the constraint where is the Euclidean vector norm
51
Department of Computer Science and Engineering, Hanyang University Freq. Domain Sol. : adjustable parameter : Fourier transform of the Laplacian operator
52
Department of Computer Science and Engineering, Hanyang University Eg. Constrained LS filter Significant improvement over Wiener filter
53
Department of Computer Science and Engineering, Hanyang University Procedure for computing Define a residual vector Adjust so that Calculation In general, automatically determined restoration filter yields inferior results to manual adjustment of filter parameters iteration
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.