templates, image pyramids, and filter banks slides largely from derek hoeim, univ. of illinois
TRANSCRIPT
![Page 1: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/1.jpg)
Templates, Image Pyramids, and Filter Banks
Slides largely from Derek Hoeim, Univ. of Illinois
![Page 2: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/2.jpg)
Followup
1. Match the spatial domain image to the Fourier magnitude image
1 54
A
32
C
B
DE
![Page 3: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/3.jpg)
Today’s class
• Template matching
• Image Pyramids
• Filter banks and texture
![Page 4: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/4.jpg)
Template matching• Goal: find in image
• Main challenge: What is a good similarity or distance measure between two patches?– Correlation– Zero-mean correlation– Sum Square Difference– Normalized Cross
Correlation
![Page 5: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/5.jpg)
Matching with filters• Goal: find in image• Method 0: filter the image with eye patch
Input Filtered Image
],[],[],[,
lnkmflkgnmhlk
What went wrong?
f = imageg = filter
![Page 6: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/6.jpg)
Matching with filters• Goal: find in image• Method 1: filter the image with zero-mean eye
Input Filtered Image (scaled) Thresholded Image
)],[()],[(],[,
lnkmfglkgnmhlk
True detections
False detections
mean of template g
![Page 7: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/7.jpg)
Matching with filters• Goal: find in image• Method 2: SSD
Input 1- sqrt(SSD) Thresholded Image
2
,
)],[],[(],[ lnkmflkgnmhlk
True detections
![Page 8: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/8.jpg)
Matching with filters
Can SSD be implemented with linear filters?2
,
)],[],[(],[ lnkmflkgnmhlk
![Page 9: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/9.jpg)
Matching with filters• Goal: find in image• Method 2: SSD
Input 1- sqrt(SSD)
2
,
)],[],[(],[ lnkmflkgnmhlk
What’s the potential downside of SSD?
![Page 10: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/10.jpg)
Matching with filters• Goal: find in image• Method 3: Normalized cross-correlation
Matlab: normxcorr2(template, im)
mean image patchmean template
5.0
,
2,
,
2
,,
)],[()],[(
)],[)(],[(
],[
lknm
lk
nmlk
flnkmfglkg
flnkmfglkg
nmh
![Page 11: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/11.jpg)
Matching with filters• Goal: find in image• Method 3: Normalized cross-correlation
Input Normalized X-Correlation Thresholded Image
True detections
![Page 12: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/12.jpg)
Matching with filters• Goal: find in image• Method 3: Normalized cross-correlation
Input Normalized X-Correlation Thresholded Image
True detections
![Page 13: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/13.jpg)
Q: What is the best method to use?
A: Depends• Zero-mean filter: fastest but not a great
matcher• SSD: next fastest, sensitive to overall intensity• Normalized cross-correlation: slowest,
invariant to local average intensity and contrast
![Page 14: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/14.jpg)
Q: What if we want to find larger or smaller eyes?
A: Image Pyramid
![Page 15: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/15.jpg)
Review of Sampling
Low-Pass Filtered ImageImage
GaussianFilter Sample
Low-Res Image
![Page 16: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/16.jpg)
Gaussian pyramid
Source: Forsyth
![Page 17: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/17.jpg)
Template Matching with Image Pyramids
Input: Image, Template1. Match template at current scale
2. Downsample image– In practice, scale step of 1.1 to 1.2
3. Repeat 1-2 until image is very small
4. Take responses above some threshold, perhaps with non-maxima suppression
![Page 18: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/18.jpg)
Laplacian filter
Gaussianunit impulse
Laplacian of Gaussian
Source: Lazebnik
![Page 19: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/19.jpg)
Laplacian pyramid
Source: Forsyth
![Page 20: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/20.jpg)
Computing Gaussian/Laplacian Pyramid
http://sepwww.stanford.edu/~morgan/texturematch/paper_html/node3.html
Can we reconstruct the original from the laplacian pyramid?
![Page 21: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/21.jpg)
Hybrid Image
![Page 22: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/22.jpg)
Hybrid Image in Laplacian PyramidHigh frequency Low frequency
In matlab on our data, and a brief project highlight.
![Page 23: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/23.jpg)
Image representation
• Pixels: great for spatial resolution, poor access to frequency
• Fourier transform: great for frequency, not for spatial info
• Pyramids/filter banks: balance between spatial and frequency information
![Page 24: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/24.jpg)
Major uses of image pyramids
• Compression
• Object detection– Scale search– Features
• Detecting stable interest points
• Registration– Course-to-fine
![Page 25: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/25.jpg)
Application: Representing Texture
Source: Forsyth
![Page 26: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/26.jpg)
Texture and Material
http://www-cvr.ai.uiuc.edu/ponce_grp/data/texture_database/samples/
![Page 27: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/27.jpg)
Texture and Orientation
http://www-cvr.ai.uiuc.edu/ponce_grp/data/texture_database/samples/
![Page 28: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/28.jpg)
Texture and Scale
http://www-cvr.ai.uiuc.edu/ponce_grp/data/texture_database/samples/
![Page 29: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/29.jpg)
What is texture?
Regular or stochastic patterns caused by bumps, grooves, and/or markings
![Page 30: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/30.jpg)
How can we represent texture?
• Compute responses of blobs and edges at various orientations and scales
![Page 31: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/31.jpg)
Overcomplete representation: filter banks
Leung-Malik (LM) Filter Bank
Code for filter banks: www.robots.ox.ac.uk/~vgg/research/texclass/filters.html
![Page 32: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/32.jpg)
Filter banks• Process image with each filter and keep
responses (or squared/abs responses)
![Page 33: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/33.jpg)
How can we represent texture?
• Measure responses of blobs and edges at various orientations and scales
• Idea 1: Record simple statistics (e.g., mean, std.) of absolute filter responses
![Page 34: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/34.jpg)
Can you match the texture to the response?
Mean abs responses
FiltersA
B
C
1
2
3
![Page 35: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/35.jpg)
Representing texture by mean abs response
Mean abs responses
Filters
![Page 36: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/36.jpg)
Representing texture• Idea 2: take vectors of filter responses at each pixel and
cluster them, then take histograms (makes good features for machine learning)
![Page 37: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/37.jpg)
How is it that a 4MP image can be compressed to a few hundred KB without a noticeable change?
Compression
![Page 38: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/38.jpg)
Lossy Image Compression (JPEG)
Block-based Discrete Cosine Transform (DCT)
Slides: Efros
![Page 39: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/39.jpg)
Using DCT in JPEG
• The first coefficient B(0,0) is the DC component, the average intensity
• The top-left coeffs represent low frequencies, the bottom right – high frequencies
![Page 40: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/40.jpg)
Image compression using DCT• Quantize
– More coarsely for high frequencies (which also tend to have smaller values)
– Many quantized high frequency values will be zero
• Encode– Can decode with inverse dct
Quantization table
Filter responses
Quantized values
![Page 41: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/41.jpg)
JPEG Compression Summary
1. Convert image to YCrCb2. Subsample color by factor of 2
– People have bad resolution for color
3. Split into blocks (8x8, typically), subtract 1284. For each block
a. Compute DCT coefficientsb. Coarsely quantize
• Many high frequency components will become zero
c. Encode (e.g., with Huffman coding)
http://en.wikipedia.org/wiki/YCbCrhttp://en.wikipedia.org/wiki/JPEG
![Page 42: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/42.jpg)
Denoising
Additive Gaussian Noise
Gaussian Filter
![Page 43: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/43.jpg)
Smoothing with larger standard deviations suppresses noise, but also blurs the image
Reducing Gaussian noise
Source: S. Lazebnik
![Page 44: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/44.jpg)
Reducing salt-and-pepper noise by Gaussian smoothing
3x3 5x5 7x7
![Page 45: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/45.jpg)
Alternative idea: Median filtering• A median filter operates over a window by
selecting the median intensity in the window
• Is median filtering linear?Source: K. Grauman
![Page 46: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/46.jpg)
Median filter• What advantage does median filtering have over
Gaussian filtering?– Robustness to outliers
Source: K. Grauman
![Page 47: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/47.jpg)
Median filterSalt-and-pepper noise Median filtered
Source: M. Hebert
• MATLAB: medfilt2(image, [h w])
![Page 48: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/48.jpg)
Median vs. Gaussian filtering3x3 5x5 7x7
Gaussian
Median
![Page 49: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/49.jpg)
Other non-linear filters• Weighted median (pixels further from center count less)
• Clipped mean (average, ignoring few brightest and darkest pixels)
• Bilateral filtering (weight by spatial distance and intensity difference)
http://vision.ai.uiuc.edu/?p=1455Image:
Bilateral filtering
![Page 50: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/50.jpg)
Bilateral filters• Edge preserving: weights similar pixels more
Carlo Tomasi, Roberto Manduchi, Bilateral Filtering for Gray and Color Images, ICCV, 1998.
Original Gaussian Bilateral
spatial similarity (e.g., intensity)
![Page 51: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/51.jpg)
Review of last three days
![Page 52: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/52.jpg)
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 0 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 0 0 0 0 0 0 0
0 0 90 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 0 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 0 0 0 0 0 0 0
0 0 90 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
Credit: S. Seitz
],[],[],[,
lnkmglkfnmhlk
[.,.]h[.,.]f
Review: Image filtering111
111
111
],[g
![Page 53: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/53.jpg)
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 0 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 0 0 0 0 0 0 0
0 0 90 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 10
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 0 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 0 0 0 0 0 0 0
0 0 90 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
],[],[],[,
lnkmglkfnmhlk
[.,.]h[.,.]f
Image filtering111
111
111
],[g
Credit: S. Seitz
![Page 54: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/54.jpg)
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 0 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 0 0 0 0 0 0 0
0 0 90 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 10 20
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 90 0 90 90 90 0 0
0 0 0 90 90 90 90 90 0 0
0 0 0 0 0 0 0 0 0 0
0 0 90 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
],[],[],[,
lnkmglkfnmhlk
[.,.]h[.,.]f
Image filtering111
111
111
],[g
Credit: S. Seitz
![Page 55: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/55.jpg)
Filtering in spatial domain-101
-202
-101
* =
![Page 56: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/56.jpg)
Filtering in frequency domain
FFT
FFT
Inverse FFT
=
![Page 57: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/57.jpg)
Review of Last 3 Days• Linear filters for basic processing
– Edge filter (high-pass)– Gaussian filter (low-pass)
FFT of Gaussian
[-1 1]
FFT of Gradient Filter
Gaussian
![Page 58: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/58.jpg)
Review of Last 3 Days• Derivative of Gaussian
![Page 59: Templates, Image Pyramids, and Filter Banks Slides largely from Derek Hoeim, Univ. of Illinois](https://reader030.vdocuments.us/reader030/viewer/2022032723/56649d0c5503460f949e1021/html5/thumbnails/59.jpg)
Review of Last 3 Days• Applications of filters
– Template matching (SSD or Normxcorr2)• SSD can be done with linear filters, is sensitive to
overall intensity
– Gaussian pyramid• Coarse-to-fine search, multi-scale detection
– Laplacian pyramid• More compact image representation• Can be used for compositing in graphics