Chapter 8: Image Restoration 8.1 Introduction
description
Transcript of Chapter 8: Image Restoration 8.1 Introduction
![Page 1: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/1.jpg)
1
Chapter 8: Image Restoration8.1 Introduction
• Image restoration concerns the removal or reduction of degradations that have occurred during the acquisition of the image
• Some restoration techniques can be performed very successfully using neighborhood operations, while others require the use of frequency domain processes
Ch8-p.191
![Page 2: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/2.jpg)
2
8.1.1 A Model of Image Degradation
f(x, y) : image h(x, y) : spatial filter
Where the symbol * represents convolution
• In practice, the noise n(x, y) must be considered
Ch8-p.191
![Page 3: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/3.jpg)
3
8.1.1 A Model of Image Degradation
• We can perform the same operations in the frequency domain, where convolution is replaced by multiplication
• If we knew the values of H and N, we could recover F by writing the above equation as
this approach may not be practical
Ch8-p.192
![Page 4: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/4.jpg)
4
8.2 Noise
• Noise—any degradation in the image signal caused by external disturbance
• These errors will appear on the image output in different ways depending on the type of disturbance in the signal
• Usually we know what type of errors to expect and the type of noise on the image; hence, we can choose the most appropriate method for reducing the effects
Ch8-p.192
![Page 5: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/5.jpg)
5
8.2.1 Salt and Pepper Noise
• Also called impulse noise, shot noise, or binary noise, salt and pepper degradation can be caused by sharp, sudden disturbances in the image signal
• Its appearance is randomly scattered white or black (or both) pixels over the image
Ch8-p.192
![Page 6: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/6.jpg)
6
FIGURE 8.1
>> imshow(t) >> figure, imshow(t_sp)
Ch8-p.193
![Page 7: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/7.jpg)
7
8.2.2 Gaussian Noise• Gaussian noise is an idealized form of white noise,
which is caused by random fluctuations in the signal
• If the image is represented as I, and the Gaussian noise by N, then we can model a noisy image by simply adding the two
Ch8-p.193
![Page 8: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/8.jpg)
8
8.2.3 Speckle Noise
• Speckle noise (or more simply just speckle) can be modeled by random values multiplied by pixel values
• It is also called multiplicative noise
• imnoise can produce speckle
Ch8-p.194
![Page 9: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/9.jpg)
9
FIGURE 8.2
Ch8-p.194
![Page 10: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/10.jpg)
10
8.2.4 Periodic Noise
Ch8-p.195
![Page 11: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/11.jpg)
11
8.3 Cleaning Salt and Pepper Noise• Low-Pass Filtering
Ch8-p.196
![Page 12: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/12.jpg)
12
8.3.2 Median Filtering
Ch8-p.197
![Page 13: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/13.jpg)
13
FIGURE 8.6
Ch8-p.198
![Page 14: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/14.jpg)
14
FIGURE 8.7
Ch8-p.198
![Page 15: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/15.jpg)
15
8.3.3 Rank-Order Filtering• Median filtering is a special case of a more
general process called rank-order filtering
• A mask as 3×3 cross shape
Ch8-p.199
0 1 01 1 10 1 0
![Page 16: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/16.jpg)
16
8.3.4 An Outlier Method• Applying the median filter can in general be a slow
operation: each pixel requires the sorting of at least nine values
• Outlier Method Choose a threshold value D For a given pixel, compare its value p with the mean m of the
values of its eight neighbors If |p − m| > D, then classify the pixel as noisy, otherwise not If the pixel is noisy, replace its value with m; otherwise leave
its value unchanged
Ch8-p.199
![Page 17: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/17.jpg)
17
FIGURE 8.8
Ch8-p.200
![Page 18: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/18.jpg)
18
FIGURE 8.9
Ch8-p.201
![Page 19: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/19.jpg)
19
8.4 Cleaning Gaussian Noise• Image Averaging
suppose we have 100 copies of our image, each with noise
Because Ni is normally distributed with mean 0, it can be readily shown that the mean of all the Ni’s will be close to zeroThe greater the number of Ni’s; the closer to zero
Ch8-p.202
![Page 20: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/20.jpg)
20
FIGURE 8.10
Ch8-p.203
![Page 21: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/21.jpg)
21
8.4.2 Average Filtering
Ch8-p.203
![Page 22: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/22.jpg)
22
8.4.3 Adaptive Filtering• Adaptive filters are a class of filters that change
their characteristics according to the values of the grayscales under the mask
Minimum mean-square error filter
The noise may not be normally distributed with mean 0
Ch8-p.204
![Page 23: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/23.jpg)
23
8.4.3 Adaptive Filtering• Wiener filters (wiener2)
Ch8-p.205
![Page 24: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/24.jpg)
24
FIGURE 8.12
Ch8-p.206
![Page 25: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/25.jpg)
25
FIGURE 8.13
Ch8-p.206
![Page 26: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/26.jpg)
26
8.5 Removal of Periodic Noise
Ch8-p.207
![Page 27: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/27.jpg)
27
FIGURE 8.15• BAND REJECT FILTERING
Ch8-p.208
![Page 28: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/28.jpg)
28
FIGURE 8.16• NOTCH FILTERING
Ch8-p.209
![Page 29: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/29.jpg)
29
8.6 Inverse Filtering
Ch8-p.210
![Page 30: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/30.jpg)
30
FIGURE 8.18
cutoff radius: 60
Ch8-p.211
![Page 31: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/31.jpg)
31
FIGURE 8.18cutoff radius: 80 cutoff radius: 100
Ch8-p.212
![Page 32: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/32.jpg)
32
FIGURE 8.19
d = 0.005
Ch8-p.213
![Page 33: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/33.jpg)
33
FIGURE 8.19d = 0.002 d = 0.001
Ch8-p.213
![Page 34: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/34.jpg)
34
8.6.1 Motion Deblurring
Ch8-p.214
![Page 35: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/35.jpg)
35
8.6.1 Motion Deblurring• To deblur the image, we need to divide its
transform by the transform corresponding to the blur filter
• This means that we first must create a matrix corresponding to the transform of the blur
Ch8-p.215
![Page 36: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/36.jpg)
36
FIGURE 8.21
Ch8-p.215
![Page 37: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/37.jpg)
37
8.7 Wiener Filtering
Ch8-p.216
![Page 38: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/38.jpg)
38
FIGURE 8.22K = 0.001
Ch8-p.217
![Page 39: Chapter 8: Image Restoration 8.1 Introduction](https://reader033.fdocuments.us/reader033/viewer/2022061509/56815c13550346895dc9efb9/html5/thumbnails/39.jpg)
39
FIGURE 8.22K = 0.0001 K = 0.00001
Ch8-p.217