Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many...
-
Upload
hugo-harper -
Category
Documents
-
view
220 -
download
0
Transcript of Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many...
![Page 1: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/1.jpg)
Image gradients and edges
Tuesday, September 1st 2015
Devi Parikh
Virginia Tech
Disclaimer: Many slides have been borrowed from Kristen Grauman, who may have borrowed some of them from others. Any time a slide did not already have a credit on it, I have credited it to Kristen. So there is a chance some of these credits are inaccurate.
![Page 2: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/2.jpg)
Announcements
• Questions?
• PS0 was due last night– 5 late
• PS1 is out– Due September 16th (Wednesday) 11:55 pm
2
Slide credit: Devi Parikh
![Page 3: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/3.jpg)
3
Topics overview
• Features & filters– Filters
• Grouping & fitting• Multiple views and motion• Recognition• Video processing
Slide credit: Kristen Grauman
![Page 4: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/4.jpg)
4
Topics overview
• Features & filters– Filters– Gradients– Edges
• Grouping & fitting• Multiple views and motion• Recognition• Video processing
Slide credit: Kristen Grauman
![Page 5: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/5.jpg)
Last time
• Image formation• Various models for image “noise”• Linear filters and convolution useful for
– Image smoothing, removing noise• Box filter• Gaussian filter• Impact of scale / width of smoothing filter
• Separable filters more efficient • Median filter: a non-linear filter, edge-preserving
5
Slide credit: Adapted by Devi Parikh from Kristen Grauman
![Page 6: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/6.jpg)
f*g=?
original image h filtered
Filter f = 1/9 x [ 1 1 1 1 1 1 1 1 1]
Review
6
Slide credit: Kristen Grauman
![Page 7: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/7.jpg)
f*g=?
Filter f = 1/9 x [ 1 1 1 1 1 1 1 1 1]T
original image h filtered
Review
7
Slide credit: Kristen Grauman
![Page 8: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/8.jpg)
Review
How do you sharpen an image?
8
Slide credit: Devi Parikh
![Page 9: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/9.jpg)
Recall: image filtering
• Compute a function of the local neighborhood at each pixel in the image– Function specified by a “filter” or mask saying how to
combine values from neighbors.
• Uses of filtering:– Enhance an image (denoise, resize, etc)– Extract information (texture, edges, etc)– Detect patterns (template matching)
10
Slide credit: Kristen Grauman, Adapted from Derek Hoiem
![Page 10: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/10.jpg)
Recall: image filtering
• Compute a function of the local neighborhood at each pixel in the image– Function specified by a “filter” or mask saying how to
combine values from neighbors.
• Uses of filtering:– Enhance an image (denoise, resize, etc)– Extract information (texture, edges, etc)– Detect patterns (template matching)
11
Slide credit: Kristen Grauman, Adapted from Derek Hoiem
![Page 11: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/11.jpg)
Edge detection
• Goal: map image from 2d array of pixels to a set of curves or line segments or contours.
• Why?
• Main idea: look for strong gradients, post-process
Figure from J. Shotton et al., PAMI 2007
12
Slide credit: Kristen Grauman
![Page 12: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/12.jpg)
What causes an edge?
Depth discontinuity: object boundary
Change in surface orientation: shape
Cast shadows
Reflectance change: appearance information, texture
13
Slide credit: Kristen Grauman
![Page 13: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/13.jpg)
Edges/gradients and invariance
14
Slide credit: Kristen Grauman
![Page 14: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/14.jpg)
Derivatives and edges
imageintensity function
(along horizontal scanline) first derivative
edges correspond toextrema of derivative
An edge is a place of rapid change in the image intensity function.
15Slide credit: Svetlana Lazebnik
![Page 15: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/15.jpg)
Derivatives with convolution
For 2D function, f(x,y), the partial derivative is:
For discrete data, we can approximate using finite differences:
To implement above as convolution, what would be the associated filter?
),(),(lim
),(0
yxfyxf
x
yxf
1
),(),1(),( yxfyxf
x
yxf
16
Slide credit: Kristen Grauman
![Page 16: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/16.jpg)
Partial derivatives of an image
Which shows changes with respect to x?
-1 1
1 -1
or?
-1 1
x
yxf
),(
y
yxf
),(
(showing filters for correlation)17
Slide credit: Kristen Grauman
![Page 17: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/17.jpg)
Assorted finite difference filters
>> My = fspecial(‘sobel’);>> outim = imfilter(double(im), My); >> imagesc(outim);>> colormap gray;
18
Slide credit: Kristen Grauman
![Page 18: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/18.jpg)
Image gradientThe gradient of an image:
The gradient points in the direction of most rapid change in intensity
The gradient direction (orientation of edge normal) is given by:
The edge strength is given by the gradient magnitude
19Slide credit: Steve Seitz
![Page 19: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/19.jpg)
Effects of noiseConsider a single row or column of the image
• Plotting intensity as a function of position gives a signal
Where is the edge?20
Slide credit: Steve Seitz
![Page 20: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/20.jpg)
Where is the edge?
Solution: smooth first
Look for peaks in 21
Slide credit: Kristen Grauman
![Page 21: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/21.jpg)
Derivative theorem of convolution
Differentiation property of convolution.
22
Slide credit: Steve Seitz
![Page 22: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/22.jpg)
11 0.0030 0.0133 0.0219 0.0133 0.0030 0.0133 0.0596 0.0983 0.0596 0.0133 0.0219 0.0983 0.1621 0.0983 0.0219 0.0133 0.0596 0.0983 0.0596 0.0133 0.0030 0.0133 0.0219 0.0133 0.0030
)()( hgIhgI
Derivative of Gaussian filters
23
Slide credit: Kristen Grauman
![Page 23: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/23.jpg)
Derivative of Gaussian filters
x-direction y-direction
24
Slide credit: Svetlana Lazebnik
![Page 24: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/24.jpg)
Derivative theorem of convolution
25
Slide credit: Steve Seitz
![Page 25: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/25.jpg)
Laplacian of Gaussian
Consider
Laplacian of Gaussianoperator
Where is the edge? Zero-crossings of bottom graph 26
Slide credit: Steve Seitz
![Page 26: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/26.jpg)
2D edge detection filters
• is the Laplacian operator:
Laplacian of Gaussian
Gaussian derivative of Gaussian
27
Slide credit: Steve Seitz
![Page 27: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/27.jpg)
Smoothing with a Gaussian
Recall: parameter σ is the “scale” / “width” / “spread” of the Gaussian kernel, and controls the amount of smoothing.
…
28
Slide credit: Kristen Grauman
![Page 28: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/28.jpg)
Effect of σ on derivatives
The apparent structures differ depending on Gaussian’s scale parameter.
Larger values: larger scale edges detectedSmaller values: finer features detected
σ = 1 pixel σ = 3 pixels
29
Slide credit: Kristen Grauman
![Page 29: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/29.jpg)
So, what scale to choose?It depends what we’re looking for.
30
Slide credit: Kristen Grauman
![Page 30: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/30.jpg)
Mask properties• Smoothing
– Values positive – Sum to 1 constant regions same as input– Amount of smoothing proportional to mask size– Remove “high-frequency” components; “low-pass” filter
• Derivatives– ___________ signs used to get high response in regions of high
contrast– Sum to ___ no response in constant regions– High absolute value at points of high contrast
31
Slide credit: Kristen Grauman
![Page 31: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/31.jpg)
Seam carving: main idea
[Shai & Avidan, SIGGRAPH 2007]
32
Slide credit: Kristen Grauman
![Page 32: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/32.jpg)
Content-aware resizing
Traditional resizing
Seam carving: main idea
[Shai & Avidan, SIGGRAPH 2007]33
Slide credit: Kristen Grauman
![Page 33: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/33.jpg)
Seam carving: main idea
34
Slide credit: Devi Parikh
![Page 34: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/34.jpg)
Content-aware resizing
Seam carving: main idea
Intuition: • Preserve the most “interesting” content
Prefer to remove pixels with low gradient energy
• To reduce or increase size in one dimension, remove irregularly shaped “seams” Optimal solution via dynamic programming.
35
Slide credit: Kristen Grauman
![Page 35: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/35.jpg)
• Want to remove seams where they won’t be very noticeable:– Measure “energy” as gradient magnitude
• Choose seam based on minimum total energy path across image, subject to 8-connectedness.
Seam carving: main idea
)( fEnergy
36
Slide credit: Kristen Grauman
![Page 36: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/36.jpg)
37
Let a vertical seam s consist of h positions that form an 8-connected path.
Let the cost of a seam be:
Optimal seam minimizes this cost:
Compute it efficiently with dynamic programming.
Seam carving: algorithm
h
iisfEnergyCost
1
))(()(s
)(min* sssCost
s1
s2
s3
s4
s5 )( fEnergy
Slide credit: Kristen Grauman
![Page 37: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/37.jpg)
How to identify the minimum cost seam?• How many possible seams are there?• First, consider a greedy approach:
625982031
Energy matrix (gradient magnitude) 38
Slide credit: Adapted by Devi Parikh from Kristen Grauman
![Page 38: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/38.jpg)
Seam carving: algorithm
39
Slide credit: Devi Parikh
If I tell you the minimum cost over all seams starting at row 1 and ending at this point
For every pixel in this row: M(i,j)
What is the minimum cost over all seams starting at row 1 and ending here?
![Page 39: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/39.jpg)
row i-1
Seam carving: algorithm• Compute the cumulative minimum energy for all possible
connected seams at each entry (i,j):
• Then, min value in last row of M indicates end of the minimal connected vertical seam.
• Backtrack up from there, selecting min of 3 above in M.
)1,1(),,1(),1,1(min),(),( jijijijiEnergyji MMMM
j-1
jrow i
M matrix: cumulative min energy
(for vertical seams)
Energy matrix(gradient magnitude)
j j+1
40
Slide credit: Kristen Grauman
![Page 40: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/40.jpg)
Example
625982031
Energy matrix(gradient magnitude)
M matrix(for vertical seams)
1458
983
031
)1,1(),,1(),1,1(min),(),( jijijijiEnergyji MMMM
41
Slide credit: Kristen Grauman
![Page 41: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/41.jpg)
Example
625982031
Energy matrix(gradient magnitude)
M matrix(for vertical seams)
1458
983
031
)1,1(),,1(),1,1(min),(),( jijijijiEnergyji MMMM
42
Slide credit: Kristen Grauman
![Page 42: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/42.jpg)
Real image example
Original Image Energy Map
Blue = low energyRed = high energy
43Slide credit: Kristen Grauman
![Page 43: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/43.jpg)
Real image example
44Slide credit: Kristen Grauman
![Page 44: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/44.jpg)
Other notes on seam carving
• Analogous procedure for horizontal seams • Can also insert seams to increase size of image
in either dimension– Duplicate optimal seam, averaged with neighbors
• Other energy functions may be plugged in– E.g., color-based, interactive,…
• Can use combination of vertical and horizontal seams
45
Slide credit: Kristen Grauman
![Page 45: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/45.jpg)
Results from Eunho Yang
Example results from students at UT Austin
46Slide credit: Kristen Grauman
![Page 46: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/46.jpg)
Results from Suyog Jain
47Slide credit: Kristen Grauman
![Page 47: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/47.jpg)
Seam carving result
Original image
Results from Martin Becker
Conventional resize
48Slide credit: Kristen Grauman
![Page 48: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/48.jpg)
Seam carving result
Conventional resize
Original image
Results from Martin Becker
49Slide credit: Kristen Grauman
![Page 49: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/49.jpg)
Results from Jay Hennig
Original image (599 by 799)
Conventional resize (399 by 599)
Seam carving (399 by 599)
50Slide credit: Kristen Grauman
![Page 50: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/50.jpg)
Results from Donghyuk Shin
Removal of a marked object
51Slide credit: Kristen Grauman
![Page 51: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/51.jpg)
Removal of a marked object
Results from Eunho Yang
52Slide credit: Kristen Grauman
![Page 52: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/52.jpg)
“Failure cases” with seam carving
By Donghyuk Shin 53Slide credit: Kristen Grauman
![Page 53: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/53.jpg)
“Failure cases” with seam carving
By Suyog Jain
54Slide credit: Kristen Grauman
![Page 54: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/54.jpg)
55
Topics overview
• Features & filters– Filters– Gradients– Edges
• Grouping & fitting• Multiple views and motion• Recognition• Video processing
Slide credit: Kristen Grauman
![Page 55: Image gradients and edges Tuesday, September 1 st 2015 Devi Parikh Virginia Tech Disclaimer: Many slides have been borrowed from Kristen Grauman, who may.](https://reader037.fdocuments.us/reader037/viewer/2022102809/56649f255503460f94c3c3ad/html5/thumbnails/55.jpg)
Questions?
See you Thursday!