Edge Detection
Many slides from Ali Farhadi, Steve Seitz, and Larry Zitnick
Edge
Attneave's Cat (1954)
Origin of edges
surface normal discontinuity
depth discontinuity
surface color discontinuity
illumination discontinuity
Edges are caused by a variety of factors
Characterizing edges
• An edge is a place of rapid change in the
image intensity function
intensity function
image (along horizontal scanline) first derivative
edges correspond to
extrema of derivative
Image gradient
• The gradient of an image:
• The gradient points in the direction of most rapid change in intensity
The discrete gradient
• How can we differentiate a digital image
F[x,y]?
– Option 1: reconstruct a continuous image, then
take gradient
– Option 2: take discrete derivative (“finite
difference”)
Image gradient
How would you implement this as a filter?
The gradient direction is given by:
How does this relate to the direction of the edge?
The edge strength is given by the gradient magnitude
Sobel operator
In practice, it is common to use:
-1 0 1 -1 -2 -1
-2 0 2 0 0 0
-1 0 1 1 2 1
Magnitude:
Orientation:
Sobel operator
Original Magnitude Orientation
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?
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?
Source: D. Forsyth
Solution: smooth first
Where is the edge? Look for peaks in
Derivative theorem of convolution
• Differentiation is convolution, and convolution is
associative: d d
( f * g) = f * g
dx dx
• This saves us one operation:
d
g
dx
d
f* g
dx
How can we find (local) maxima of a function? Source: S. Seitz
Edge detection by subtraction
original
Edge detection by subtraction
smoothed (5x5 Gaussian)
Edge detection by subtraction
Why does
this work?
smoothed – original
(scaled by 4, offset +128)
Gaussian - image filter
Gaussian delta function
Laplacian of Gaussian
Canny edge detector
• This is probably the most widely used edge
detector in computer vision
J. Canny, A Computational Approach To Edge Detection, IEEE Trans. Pattern
Analysis and Machine Intelligence, 8:679-714, 1986.
Source: L. Fei-Fei
The Canny edge detector
• original image (Lena)
The Canny edge detector
norm of the gradient
The Canny edge detector
thresholding
Get Orientation at Each Pixel
theta = atan2(-gy, gx)
The Canny edge detector
The Canny edge detector
thinning
(non-maximum suppression)
If not, suppress (i.e. remove) the value.
Non-maximum suppression
mple example of non-maximum suppression is shown in Figure 4. Almost all pixels ha
dient directions pointing north. They are therefore compared with the pixels above a
w. The pixels that turn out to be maximal in this comparison are marked with wh
ders. All other pixels will be suppressed. Figure 5 shows the effect on the test image.
2 3 5 4 6
4 5 7 6 7
5 6 4 3 2
3 4 3 1 1
ure 4: Illustration of non-maximum suppression. The edge strengths are indicated both as colors a
bers, while the gradient directions are shown as arrows. The resulting edge pixels are marked w
• Check if pixel is local maximum along
e borders.
gradient direction
4
Picture from Prem K Kalra
Compute Gradients (DoG)
X-Derivative of Gaussian Y-Derivative of Gaussian Gradient Magnitude
Canny Edges
Effect of s (Gaussian kernel spread/size)
original Canny with Canny with
The choice of depends on desired behavior
• large detects large scale edges
• small detects fine features
An edge is not a line...
How can we detect lines ?
Finding lines in an image
• Option 1:
– Search for the line at every possible
position/orientation
– What is the cost of this operation?
• Option 2:
– Use a voting scheme: Hough transform
Finding lines in an image
y b
b0
x m0 m
image space Hough space
• Connection between image (x,y) and Hough
(m,b) spaces
– A line in the image corresponds to a point in Hough
space
– To go from image space to Hough space:
• given a set of points (x,y), find all (m,b) such that y = mx + b
Finding lines in an image
y b
y0
x0 x m
image space Hough space
• Connection between image (x,y) and Hough (m,b) spaces
– A line in the image corresponds to a point in Hough space
– To go from image space to Hough space:
• given a set of points (x,y), find all (m,b) such that y = mx + b
– What does a point (x0, y0) in the image space map to?
– A: the solutions of b = -x0m + y0
– this is a line in Hough space
Hough transform algorithm
• Typically use a different parameterization
– d is the perpendicular distance from the line
to the origin
– q is the angle
Hough transform algorithm
• Basic Hough transform algorithm
1. Initialize H[d, q]=0
2. for each edge point I[x,y] in the image
for q = 0 to 180
H[d, q] += 1
3. Find the value(s) of (d, q) where H[d, q] is maximum
4. The detected line in the image is given by
• What’s the running time (measured in # votes)?
Hough transform algorithm
[Link]
Hough transform algorithm
[Link]
Extensions
• Extension 1: Use the image gradient
1. same
2. for each edge point I[x,y] in the image
compute unique (d, q) based on image gradient at (x,y)
H[d, q] += 1
3. same
4. same
• What’s the running time measured in votes?
• Extension 2
– give more votes for stronger edges
• Extension 3
– change the sampling of (d, q) to give more/less resolution
• Extension 4
– The same procedure can be used with circles, squares, or any other
shape, How?