1. Program Studi S-1 Teknik Informatika FMIPA Universitas Padjadjaran
COMPUTER VISION D10K-7C02 CV04: Image FIltering Dr. Setiawan Hadi, M.Sc.CS.
Program Studi S-1 Teknik Informatika
FMIPA Universitas Padjadjaran

2. Motion illusion, rotating snakes

3. Dari 3D ke 2D

4. Recognition Concept

5. Image Filtering
Compute function of local neighborhood at each position
Usage
Enhance images
Denoise, resize, increase contrast, etc.
Extract information from images
Texture, edges, distinctive points, etc.
Detect patterns
Template matching

6. Image Filtering Types Image filters in spatial domain
Filter is a mathematical operation of a grid of numbers
Smoothing, sharpening, measuring texture
Image filters in the frequency domain
Filtering is a way to modify the frequencies of images
Denoising, sampling, image compression
Templates and Image Pyramids
Filtering is a way to match a template to the image
Detection, coarse-to-fine registration

7. Filter What does it do? Box filter
Replaces each pixel with an average of its neighborhood
Achieve smoothing effect (remove sharp features 1

8. Image Filtering Operation1

9. Image Filtering Operation1 90 90
ones, divide by 9
Credit: S. Seitz

10. Image Filtering Operation1 90 90 10
ones, divide by 9
Credit: S. Seitz

11. Image Filtering Operation1 90 90 10 20
ones, divide by 9
Credit: S. Seitz

12. Image Filtering Operation1 90 90 10 20 30
ones, divide by 9
Credit: S. Seitz

13. Image Filtering Operation1 90 10 20 30

14. Image Filtering Operation1 90 10 20 30 ?

15. Image Filtering Operation1 90 10 20 30 50 ?
Credit: S. Seitz

16. Image Filtering Operation1 90 10 20 30 40 60 90 50 80
Credit: S. Seitz

17. Image Filtering Example

18. Linear Filter 1 ?
Original

19. Linear Filter 1
Original
Filtered
(no change)

20. Linear Filter 1 ?
Original

21. Linear Filter 1
Original
Shifted left
By 1 pixel

22. Linear Filter - 2 1 ?
(Note that filter sums to 1)
Original

23. - Linear Filter 2 1 Original Sharpening filter2 1
Original
Sharpening filter
Accentuates differences with local average

24. Sharpening

25. Other Filter -1 -2 1 2
Sobel
Horizontal Edge
(absolute value)

26. Filtering vs Convolution

27. Gaussian FIlter
5 x 5,  = 1

28. Example of Gaussian Filter

29. Median Filter
operates over a window by selecting the median intensity in the window.
What advantage does a median filter have over a mean filter?
Is a median filter a kind of convolution?

30. Salt and Pepper Noise Removal by Mean filter Gaussian filter
Median filter

31. Measuring Image Quality
Image quality is a characteristic of an image that measures the perceived image degradation (typically, compared to an ideal or perfect image).
Measurement tools
PNSR Peak to Signal Noise Ration

32. Illustration PNSR

33. Demo Filter

34. Exercise
Write down a 3x3 filter that returns a positive value if the average value of the 4-adjacent neighbors is less than the center and a negative value otherwise
Write down a filter that will compute the gradient in the x-direction:
gradx(y,x) = im(y,x+1)-im(y,x) for each x, y

35. 3. Fill in the blanks: a) _ = D * B b) A = _ * _ c) F = D * _
Filtering Operator
a) _ = D * B
b) A = _ * _
c) F = D * _
d) _ = D * D
3. Fill in the blanks: A B E G C F D H I