Title: Stanford CS223B Computer Vision, Winter 2005 Lecture 3 Filters and Features (with Matlab)
1Stanford CS223B Computer Vision, Winter
2005Lecture 3 Filters and Features (with
Matlab)
- Sebastian Thrun, Stanford
- Rick Szeliski, Microsoft
- Hendrik Dahlkamp, Stanford
- with slides by D Forsyth, D. Lowe, M.
Polleyfeys, C. Rasmussen, G. Loy, D. Jacobs, J.
Rehg, A, Hanson, G. Bradski,
2Assignment 1 FAQ
- Compiling projects
- cxcored.dll is the debug version of cxcore.dll,
can be compiled from cxcore.dsp - Use template cvsample.dsp to get paths right
- Taking the images
- Assignment change out-of-focus images no longer
needed - Dont print a border around the chessboard
3Assignment 1 FAQ
- Corner finding
- Supply correct parameters e.g. corner_countltgt0
- Visualize corner ordering
- How to verify results
- Backproject scene corners into image
- Use common sense
etc
4Stanford CS223B Computer Vision, Winter
2005Lecture 3 Filters and Features (with
Matlab)
- Sebastian Thrun, Stanford
- Rick Szeliski, Microsoft
- Hendrik Dahlkamp, Stanford
- with slides by D Forsyth, D. Lowe, M.
Polleyfeys, C. Rasmussen, G. Loy, D. Jacobs, J.
Rehg, A, Hanson, G. Bradski,
5Todays Goals
- Features 101
- Linear Filters and Edge Detection
- Canny Edge Detector
6Todays Question
- What is a feature?
- What is an image filter?
- How can we find corners?
- How can we find edges?
7What is a Feature?
- Local, meaningful, detectable parts of the image
8Features in Computer Vision
- What is a feature?
- Location of sudden change
- Why use features?
- Information content high
- Invariant to change of view point, illumination
- Reduces computational burden
9(One Type of) Computer Vision
Feature 1 Feature 2 Feature N
Computer Vision Algorithm
10Where Features Are Used
- Calibration
- Image Segmentation
- Correspondence in multiple images (stereo,
structure from motion) - Object detection, classification
11What Makes For Good Features?
- Invariance
- View point (scale, orientation, translation)
- Lighting condition
- Object deformations
- Partial occlusion
- Other Characteristics
- Uniqueness
- Sufficiently many
- Tuned to the task
12Todays Goals
- Features 101
- Linear Filters and Edge Detection
- Canny Edge Detector
13What Causes an Edge?
- Depth discontinuity
- Surface orientation discontinuity
- Reflectance discontinuity (i.e., change in
surface material properties) - Illumination discontinuity (e.g., shadow)
Slide credit Christopher Rasmussen
14Quiz How Can We Find Edges?
15Edge Finding 101
- im imread('bridge.jpg')
- image(im)
- figure(2)
- bw double(rgb2gray(im))
- image(bw)
- gradkernel -1 1
- dx abs(conv2(bw, gradkernel, 'same'))
- image(dx)
- colorbar colormap gray
- dx,dy gradient(bw)
- gradmag sqrt(dx.2 dy.2)
- image(gradmag)
matlab
colorbar colormap(gray(255)) colormap(default)
16Edge Finding 101
- Example of a linear Filter
17What is Image Filtering?
- Modify the pixels in an image based on some
function of a local neighborhood of the pixels
10 5 3
4 5 1
1 1 7
7
Some function
18Linear Filtering
- Linear case is simplest and most useful
- Replace each pixel with a linear combination of
its neighbors. - The prescription for the linear combination is
called the convolution kernel.
10 5 3
4 5 1
1 1 7
7
0 0 0
0 0.5 0
0 1.0 0.5
kernel
19Linear Filter Convolution
f (i,j)
20Linear Filter Convolution
21Filtering Examples
22Filtering Examples
23Filtering Examples
24Image Smoothing With Gaussian
- figure(3)
- sigma 3
- width 3 sigma
- support -width width
- gauss2D exp( - (support / sigma).2 / 2)
- gauss2D gauss2D / sum(gauss2D)
- smooth conv2(conv2(bw, gauss2D, 'same'),
gauss2D', 'same') - image(smooth)
- colormap(gray(255))
- gauss3D gauss2D' gauss2D
- tic smooth conv2(bw,gauss3D, 'same') toc
25Smoothing With Gaussian
Slide credit Marc Pollefeys
26Smoothing Reduces Noise
The effects of smoothing Each row shows
smoothing with gaussians of different width each
column shows different realizations of an image
of gaussian noise.
Slide credit Marc Pollefeys
27Example of Blurring
Image
Blurred Image
-
28Edge Detection With Smoothed Images
- figure(4)
- dx,dy gradient(smooth)
- gradmag sqrt(dx.2 dy.2)
- gmax max(max(gradmag))
- imshow(gradmag)
- colormap(gray(gmax))
29Scale
- Increased smoothing
- Eliminates noise edges.
- Makes edges smoother and thicker.
- Removes fine detail.
30The Edge Normal
31Displaying the Edge Normal
- figure(5)
- hold on
- image(smooth)
- colormap(gray(255))
- m,n size(gradmag)
- edges (gradmag gt 0.3 gmax)
- inds find(edges)
- posx,posy meshgrid(1n,1m)
posx2posx(inds) posy2posy(inds) - gm2 gradmag(inds)
- sintheta dx(inds) ./ gm2
- costheta - dy(inds) ./ gm2
- quiver(posx2,posy2, gm2 . sintheta / 10, -gm2 .
costheta / 10,0) - hold off
32Separable Kernels
33Combining Kernels / Convolutions
34Effect of Smoothing Radius
1 pixel
3 pixels
7 pixels
35Roberts Cross Operator
S
or
I(x, y) - I(x1, y1) I(x, y1) - I(x1,
y)
S
36Sobel Operator
-1 -2 -1 0 0 0 1 2 1
-1 0 1 -2 0 2 -1 0 1
S1
S2
37The Sobel Kernel, Explained
Sobel kernel is separable!
Averaging done parallel to edge
38Sobel Edge Detector
- figure(6)
- edge(bw, 'sobel')
39Robinson Compass Masks
40Claim Your Own Kernel!
41Comparison (by Allan Hanson)
- Analysis based on a step edge inclined at an
angle q (relative to y-axis) through center of
window. - Robinson/Sobel true edge contrast less than 1.6
different from that computed by the operator. - Error in edge direction
- Robinson/Sobel less than 1.5 degrees error
- Prewitt less than 7.5 degrees error
- Summary
- Typically, 3 x 3 gradient operators perform
better than 2 x 2. - Prewitt2 and Sobel perform better than any of the
other 3x3 gradient estimation operators. - In low signal to noise ratio situations, gradient
estimation operators of size larger than 3 x 3
have improved performance. - In large masks, weighting by distance from the
central pixel is beneficial.
42Todays Goals
- Features 101
- Linear Filters and Edge Detection
- Canny Edge Detector
43Canny Edge Detector
- figure(7)
- edge(bw, 'canny')
44Canny Edge Detection
- Steps
- Apply derivative of Gaussian
- Non-maximum suppression
- Thin multi-pixel wide ridges down to single
pixel width - Linking and thresholding
- Low, high edge-strength thresholds
- Accept all edges over low threshold that are
connected to edge over high threshold
45Non-Maximum Supression
Non-maximum suppression Select the single
maximum point across the width of an edge.
46Linking to the Next Edge Point
Assume the marked point is an edge point. Take
the normal to the gradient at that point and use
this to predict continuation points (either r or
s).
47Edge Hysteresis
- Hysteresis A lag or momentum factor
- Idea Maintain two thresholds khigh and klow
- Use khigh to find strong edges to start edge
chain - Use klow to find weak edges which continue edge
chain - Typical ratio of thresholds is roughly
- khigh / klow 2
48Canny Edge Detection (Example)
Strong connected weak edges
Original image
Strong edges only
Weak edges
courtesy of G. Loy
49Canny Edge Detection (Example)
Using Matlab with default thresholds
50Application Road Finding
- (add roadrunner video here)
51Corner Effects
52Todays Goals
- Features 101
- Linear Filters and Edge Detection
- Canny Edge Detector