cse 185 introduction to computer vision
DESCRIPTION
CSE 185 Introduction to Computer Vision. Edges. Edges. Edges Scale space Reading: Chapter 3 of S. Edge detection. Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded in the edges - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/1.jpg)
CSE 185 Introduction to Computer
VisionEdges
![Page 2: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/2.jpg)
Edges
• Edges• Scale space
• Reading: Chapter 3 of S
![Page 3: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/3.jpg)
Edge detection• Goal: Identify sudden
changes (discontinuities) in an image– Intuitively, most semantic
and shape information from the image can be encoded in the edges
– More compact than pixels• Ideal: artist’s line
drawing (but artist is also using object-level knowledge)
![Page 4: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/4.jpg)
Why do we care about edges?• Extract information,
recognize objects
• Recover geometry and viewpoint
Vanishing point
Vanishing
line
Vanishing point
Vertical vanishing point
(at infinity)
![Page 5: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/5.jpg)
Origin of Edges
• Edges are caused by a variety of factors
depth discontinuity
surface color discontinuity
illumination discontinuity
surface normal discontinuity
![Page 6: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/6.jpg)
Marr’s theory
![Page 7: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/7.jpg)
Example
![Page 8: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/8.jpg)
Closeup of edges
Source: D. Hoiem
![Page 9: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/9.jpg)
Closeup of edges
![Page 10: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/10.jpg)
Closeup of edges
![Page 11: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/11.jpg)
Closeup of edges
![Page 12: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/12.jpg)
Characterizing edges• An edge is a place of rapid change in the
image intensity function
imageintensity function
(along horizontal scanline) first derivative
edges correspond toextrema of derivative
![Page 13: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/13.jpg)
Intensity profile
![Page 14: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/14.jpg)
With a little Gaussian noise
Gradient
![Page 15: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/15.jpg)
Effects of noise• Consider a single row or column of the image
– Plotting intensity as a function of position gives a signal
Where is the edge?
![Page 16: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/16.jpg)
Effects of noise
• Difference filters respond strongly to noise– Image noise results in pixels that look
very different from their neighbors– Generally, the larger the noise the
stronger the response
• What can we do about it?
![Page 17: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/17.jpg)
Solution: smooth first
• To find edges, look for peaks in )( gfdx
d
f
g
f * g
)( gfdx
d
![Page 18: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/18.jpg)
• Differentiation is convolution, and convolution is associative:
• This saves us one operation:
gdx
dfgf
dx
d )(
Derivative theorem of convolution
gdx
df
f
gdx
d
![Page 19: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/19.jpg)
Derivative of Gaussian filter
* [1 -1] =
![Page 20: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/20.jpg)
Differentiation and convolution• Recall
• Now this is linear and shift invariant, so must be the result of a convolution
• We could approximate this as
(which is obviously a convolution; it’s not a very good way to do things, as we shall see)
),(),(lim
0
yxfyxf
x
f
x
yxfyxf
x
f nn
),(),( 1
000
101
000
H
![Page 21: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/21.jpg)
Discrete edge operators• How can we differentiate a discrete image?
Finite difference approximations:
1, jiI 1,1 jiI
jiI , jiI ,1
Convolution masks :
jijijiji
jijijiji
IIIIy
I
IIIIx
I
,1,,11,1
,,11,1,1
2
12
1
2
1
x
I
2
1
y
I
![Page 22: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/22.jpg)
1, jiI 1,1 jiI
jiI , jiI ,1
1,1 jiI
jiI ,1
1,1 jiI 1, jiI 1,1 jiI
• Second order partial derivatives:
• Laplacian :
Convolution masks :
or
Discrete edge operators
(more accurate)
1 4 1
4 -20 4
1 4 1
0 1 0
1 -4 1
0 1 0
1,,1,22
2
,1,,122
2
21
21
jijiji
jijiji
IIIy
I
IIIx
I
2
2
2
22
y
I
x
II
22 1
I
26
1
![Page 23: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/23.jpg)
Finite differences
Partial derivative in y axis, respond strongly tohorizontal edges
Partial derivative in x axis, respond strongly to vertical edges
![Page 24: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/24.jpg)
Spatial filter
• Approximation
|)||)(|||
|)||)(|||
|)||)(|||
])()[(||
||,
8695
2/18695
6585
2/1265
285
2/122
zzzzf
zzzzf
zzzzf
zzzzf
y
f
x
ff
y
fx
f
f
987
654
321
zzz
zzz
zzz
![Page 25: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/25.jpg)
Roberts operator
One of the earliest edge detection algorithm by Lawrence Roberts
Convolve image with to get Gx and Gy
![Page 26: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/26.jpg)
Sobel operatorOne of the earliest edge detection algorithm by Irwine Sobel
![Page 27: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/27.jpg)
Image gradient• Gradient equation:
• Represents direction of most rapid change in intensity
• Gradient direction:
• The edge strength is given by the gradient magnitude
![Page 28: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/28.jpg)
2D Gaussian edge operators
Laplacian of GaussianGaussian Derivative of Gaussian (DoG)
Mexican Hat (Sombrero)• is the Laplacian operator:
Marr-Hildreth algorithm
![Page 29: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/29.jpg)
• Smoothed derivative removes noise, but blurs edge. Also finds edges at different “scales”.
1 pixel 3 pixels 7 pixels
Tradeoff between smoothing and localization
![Page 30: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/30.jpg)
• The gradient magnitude is large along a thick “trail” or “ridge,” so how do we identify the actual edge points?
• How do we link the edge points to form curves?
Implementation issues
![Page 31: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/31.jpg)
Designing an edge detector• Criteria for a good edge detector:
– Good detection: the optimal detector should find all real edges, ignoring noise or other artifacts
– Good localization•the edges detected must be as close as
possible to the true edges•the detector must return one point only for
each true edge point• Cues of edge detection
– Differences in color, intensity, or texture across the boundary
– Continuity and closure– High-level knowledge
![Page 32: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/32.jpg)
Canny edge detector• Probably the most widely used edge
detector in computer vision• Theoretical model: step-edges
corrupted by additive Gaussian noise• Canny has shown that the first
derivative of the Gaussian closely approximates the operator that optimizes the product of signal-to-noise ratio and localization
J. Canny, A Computational Approach To Edge Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, 8:679-714, 1986.
http://www.mathworks.com/discovery/edge-detection.html
![Page 33: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/33.jpg)
Example
original image (Lena)
![Page 34: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/34.jpg)
Derivative of Gaussian filter
x-direction y-direction
![Page 35: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/35.jpg)
Compute gradients
X-Derivative of Gaussian Y-Derivative of Gaussian Gradient Magnitude
![Page 36: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/36.jpg)
Get orientation at each pixel
• Threshold at minimum level• Get orientation theta = atan2(gy, gx)
![Page 37: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/37.jpg)
Non-maximum suppression for each orientation
At q, we have a maximum if the value is larger than those at both p and at r. Interpolate to get these values.
![Page 38: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/38.jpg)
Assume the marked point is an edge point. Then we construct the tangent to the edge curve (which is normal to the gradient at that point) and use this to predict the next points (here either r or s).
Edge linking
![Page 39: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/39.jpg)
Sidebar: Bilinear Interpolation
http://en.wikipedia.org/wiki/Bilinear_interpolation
![Page 40: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/40.jpg)
Sidebar: Interpolation options• imx2 = imresize(im, 2,
interpolation_type)
• ‘nearest’ – Copy value from nearest known– Very fast but creates blocky edges
• ‘bilinear’– Weighted average from four nearest known
pixels– Fast and reasonable results
• ‘bicubic’ (default)– Non-linear smoothing over larger area (4x4)– Slower, visually appealing, may create
negative pixel values
![Page 41: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/41.jpg)
Before non-max suppression
![Page 42: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/42.jpg)
After non-max suppression
![Page 43: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/43.jpg)
Hysteresis thresholding• Threshold at low/high levels to get weak/strong edge pixels• Do connected components, starting from strong edge pixels
![Page 44: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/44.jpg)
Hysteresis thresholding
• Check that maximum value of gradient value is sufficiently large– drop-outs? use hysteresis
• use a high threshold to start edge curves and a low threshold to continue them.
Source: S. Seitz
![Page 45: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/45.jpg)
Final Canny edges
![Page 46: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/46.jpg)
Canny edge detector
1. Filter image with x, y derivatives of Gaussian 2. Find magnitude and orientation of gradient3. Non-maximum suppression:
– Thin multi-pixel wide “ridges” down to single pixel width
4. Thresholding and linking (hysteresis):– Define two thresholds: low and high– Use the high threshold to start edge curves and
the low threshold to continue them
• MATLAB: edge(image, ‘canny’)
![Page 47: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/47.jpg)
Effect of (Gaussian kernel size)
Canny with Canny with original
The choice of depends on desired behavior• large detects large scale edges• small detects fine features
![Page 48: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/48.jpg)
Where do humans see boundaries?
• Berkeley segmentation database:http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/segbench/
image human segmentation gradient magnitude
![Page 49: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/49.jpg)
pB boundary detector
Martin, Fowlkes, Malik 2004: Learning to Detect Natural Boundaries…http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/papers/mfm-pami-boundary.pdf
![Page 50: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/50.jpg)
Brightness
Color
Texture
Combined
Human
![Page 51: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/51.jpg)
Human (0.95)
Pb (0.88)
![Page 52: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/52.jpg)
State of edge detection
• Local edge detection works well– But many false positives from
illumination and texture edges
• Some methods to take into account longer contours, but could probably do better
• Poor use of object and high-level information
![Page 53: CSE 185 Introduction to Computer Vision](https://reader035.vdocument.in/reader035/viewer/2022062520/568159c9550346895dc71bcc/html5/thumbnails/53.jpg)
Sketching
• Learn from artist’s strokes so that edges are more likely in certain parts of the face.
Berger et al. SIGGRAPH 2013