Feature matching

“What stuff in the left image matches with stuff on the right?”

Necessary for automatic panorama stitching

(Part of Project 4!)

Slides from Steve Seitz and Rick Szeliski

Image matching

by Diva Sian

by swashford
Harder case

by Diva Sian by scgbt

Harder still?

NASA Mars Rover images

Answer below (look for tiny colored squares…)

NASA Mars Rover images

with SIFT feature matches
Figure by Noah Snavely
Features

Back to (more-or-less) established material

We can use textbook!
Reading HW: Szeliski, Ch 4.1
 Image Matching

1) At an interesting point, let’s define a coordinate system (x,y axis)

2) Use the coordinate system to pull out a patch at that point
Image Matching
 Invariant local features
-Algorithm for finding points and representing their patches should
produce similar results even when conditions vary
-Buzzword is “invariance”
• geometric invariance: translation, rotation, scale
• photometric invariance: brightness, exposure, …

Feature Descriptors
 What makes a good feature?

Say we have 2 images of this scene we’d like to align by matching local features
What would be the good local features (ones easy to match)?
Want uniqueness
Look for image regions that are unusual
• Lead to unambiguous matches in other images

How to define “unusual”?

Local measures of uniqueness
Suppose we only consider a small window of pixels
• What defines whether a feature is a good or bad candidate?

Slide adapted from Darya Frolova, Denis Simakov, Weizmann Institute.

Feature detection
Local measure of feature uniqueness
• How does the window change when you shift it?
• Shifting the window in any direction causes a big change

“flat” region: “edge”: “corner”:

no change in all no change along significant change
directions the edge direction in all directions

Slide adapted from Darya Frolova, Denis Simakov, Weizmann Institute.

Feature detection: the math
Consider shifting the window W by (u,v)
• how do the pixels in W change?
• compare each pixel before and after by
summing up the squared differences (SSD) W
• this defines an SSD “error” of E(u,v):
Small motion assumption
Taylor Series expansion of I:

If the motion (u,v) is small, then first order approx is good

Plugging this into the formula on the previous slide…

Feature detection: the math
Consider shifting the window W by (u,v)
• how do the pixels in W change?
• compare each pixel before and after by
summing up the squared differences W
• this defines an “error” of E(u,v):
Feature detection: the math
This can be rewritten:

For the example above

• You can move the center of the green window to anywhere on the
blue unit circle
• Which directions will result in the largest and smallest E values?
• We can find these directions by looking at the eigenvectors of H
Quick eigenvalue/eigenvector review
The eigenvectors of a matrix A are the vectors x that satisfy:

The scalar  is the eigenvalue corresponding to x

• The eigenvalues are found by solving:

• In our case, A = H is a 2x2 matrix, so we have

• The solution:

Once you know , you find x by solving

Feature detection: the math

x-

x+

Eigenvalues and eigenvectors of H

• Define shifts with the smallest and largest change (E value)
• x+ = direction of largest increase in E.
 + = amount of increase in direction x+
• x- = direction of smallest increase in E.
 - = amount of increase in direction x
Feature detection: the math
How are +, x+, -, and x+ relevant for feature detection?
• What’s our feature scoring function?
Feature detection: the math
How are +, x+, -, and x+ relevant for feature detection?
• What’s our feature scoring function?

Want E(u,v) to be large for small shifts in all directions

• the minimum of E(u,v) should be large, over all unit vectors [u v]
• this minimum is given by the smaller eigenvalue (-) of H
Feature detection summary
Here’s what you do
• Compute the gradient at each point in the image
• Create the H matrix from the entries in the gradient
• Compute the eigenvalues.
• Find points with large response (- > threshold)
• Choose those points where - is a local maximum as features
Feature detection summary
Here’s what you do
• Compute the gradient at each point in the image
• Create the H matrix from the entries in the gradient
• Compute the eigenvalues.
• Find points with large response (- > threshold)
• Choose those points where - is a local maximum as features
The Harris operator
- is a variant of the “Harris operator” for feature detection

• The trace is the sum of the diagonals, i.e., trace(H) = h11 + h22
• Very similar to - but less expensive (no square root)
• Called the “Harris Corner Detector” or “Harris Operator”
• Lots of other detectors, this is one of the most popular
The Harris operator

Harris
operator
Harris detector example
f value (red high, blue low)
Threshold (f > value)
Find local maxima of f
Harris features (in red)

The tops of the horns are detected in both images

Invariance
Suppose you rotate the image by some angle
• Will you still pick up the same features?

What if you change the brightness?

Scale?
Scale invariant detection
Suppose you’re looking for corners

Key idea: find scale that gives local maximum of f

• f is a local maximum in both position and scale
• Common definition of f: Laplacian
(or difference between two Gaussian filtered images with different sigmas)
 Lindebergetetal,
Lindeberg al.,1996
1996

Slide
Slidefrom
fromTinne
TinneTuytelaars
Tuytelaars
Feature descriptors
We know how to detect good points
Next question: How to match them?

?
Feature descriptors
We know how to detect good points
Next question: How to match them?

?
Lots of possibilities (this is a popular research area)
• Simple option: match square windows around the point
• State of the art approach: SIFT
– David Lowe, UBC http://www.cs.ubc.ca/~lowe/keypoints/
Invariance
Suppose we are comparing two images I1 and I2
• I2 may be a transformed version of I1
• What kinds of transformations are we likely to encounter in
practice?
Invariance
Suppose we are comparing two images I 1 and I2
• I2 may be a transformed version of I1
• What kinds of transformations are we likely to encounter in
practice?

We’d like to find the same features regardless of the

transformation
• This is called transformational invariance
• Most feature methods are designed to be invariant to
– Translation, 2D rotation, scale
• They can usually also handle
– Limited 3D rotations (SIFT works up to about 60 degrees)
– Limited affine transformations (2D rotation, scale, shear)
– Limited illumination/contrast changes
How to achieve invariance
Need both of the following:
1. Make sure your detector is invariant
• Harris is invariant to translation and rotation
• Scale is trickier
– common approach is to detect features at many scales using a
Gaussian pyramid (e.g., MOPS)
– More sophisticated methods find “the best scale” to represent
each feature (e.g., SIFT)
2. Design an invariant feature descriptor
• A descriptor captures the information in a region around the
detected feature point
• The simplest descriptor: a square window of pixels
– What’s this invariant to?
• Let’s look at some better approaches…
Rotation invariance for feature descriptors
Find dominant orientation of the image patch
• This is given by x+, the eigenvector of H corresponding to +
 + is the larger eigenvalue
• Rotate the patch according to this angle

Figure by Matthew Brown

Multiscale Oriented PatcheS descriptor
Take 40x40 square window around detected feature
• Scale to 1/5 size (using prefiltering)
• Rotate to horizontal
• Sample 8x8 square window centered at feature
• Intensity normalize the window by subtracting the mean, dividing by the
standard deviation in the window (both window I and aI+b will match)

40 p
ixels 8 pixels

CSE 576: Computer Vision

Adapted from slide by Matthew Brown

Detections at multiple scales
Scale Invariant Feature Transform
Basic idea:
• Take 16x16 square window around detected feature
• Compute edge orientation (angle of the gradient - 90) for each pixel
• Throw out weak edges (threshold gradient magnitude)
• Create histogram of surviving edge orientations

0 2
angle histogram

Adapted from slide by David Lowe

SIFT descriptor
Full version
• Divide the 16x16 window into a 4x4 grid of cells (2x2 case shown below)
• Compute an orientation histogram for each cell
• 16 cells * 8 orientations = 128 dimensional descriptor

Adapted from slide by David Lowe

Properties of SIFT
Extraordinarily robust matching technique
• Can handle changes in viewpoint
– Up to about 60 degree out of plane rotation
• Can handle significant changes in illumination
– Sometimes even day vs. night (below)
• Fast and efficient—can run in real time
• Lots of code available
– http://people.csail.mit.edu/albert/ladypack/wiki/index.php/Known_implementations_of_SIFT
 Maximally Stable Extremal Regions
J.Matas et.al. “Distinguished Regions for Wide-baseline Stereo”. BMVC 2002.

• Maximally Stable Extremal Regions

• Threshold image intensities: I > thresh
for several increasing values of thresh
• Extract connected components
(“Extremal Regions”)
• Find a threshold when region is
“Maximally Stable”, i.e. local minimum
of the relative growth
• Approximate each region with
an ellipse
Feature matching
Given a feature in I1, how to find the best match in I2?
1. Define distance function that compares two descriptors
2. Test all the features in I2, find the one with min distance
Feature distance
How to define the difference between two features f1, f2?
• Simple approach is SSD(f1, f2)
– sum of square differences between entries of the two descriptors
– can give good scores to very ambiguous (bad) matches

f1 f2

I1 I2
Feature distance
How to define the difference between two features f1, f2?
• Better approach: ratio distance = SSD(f1, f2) / SSD(f1, f2’)
– f2 is best SSD match to f1 in I2
– f2’ is 2nd best SSD match to f1 in I2
– gives small values for ambiguous matches

f1 f2' f2

I1 I2
Evaluating the results
How can we measure the performance of a feature matcher?

50
75
200

feature distance
True/false positives

50
true match
75
200
false match

feature distance

The distance threshold affects performance

• True positives = # of detected matches that are correct
– Suppose we want to maximize these—how to choose threshold?
• False positives = # of detected matches that are incorrect
– Suppose we want to minimize these—how to choose threshold?
 Evaluating the results
How can we measure the performance of a feature matcher?

0.7

# true positives true

# matching features (positives) positive
rate

0 0.1 false positive rate 1

# false positives
# unmatched features (negatives)
 Evaluating the results
How can we measure the performance of a feature matcher?
ROC curve (“Receiver Operator Characteristic”)
1

0.7

# true positives true

# matching features (positives) positive
rate

0 0.1 false positive rate 1

# false positives
# unmatched features (negatives)
ROC Curves
• Generated by counting # current/incorrect matches, for different threholds
• Want to maximize area under the curve (AUC)
• Useful for comparing different feature matching methods
• For more info: http://en.wikipedia.org/wiki/Receiver_operating_characteristic
More on feature detection/description
Lots of applications
Features are used for:
• Image alignment (e.g., mosaics)
• 3D reconstruction
• Motion tracking
• Object recognition
• Indexing and database retrieval
• Robot navigation
• … other
Object recognition (David Lowe)