Scribd
Upload
1 views

lecture5-2 (1)

The document outlines the main components of local feature detection, including detection, description, and matching of interest points in images. It discusses the Harris detector's invariance properties to image transformations such as translation and intensity changes, as well as the concept of scale-invariant detection. Additionally, it introduces the Laplacian of Gaussian (LoG) for feature extraction and highlights the importance of feature descriptors for matching detected points across images.

Uploaded by

asumi288hk
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
1 views

lecture5-2 (1)

The document outlines the main components of local feature detection, including detection, description, and matching of interest points in images. It discusses the Harris detector's invariance properties to image transformations such as translation and intensity changes, as well as the concept of scale-invariant detection. Additionally, it introduces the Laplacian of Gaussian (LoG) for feature extraction and highlights the importance of feature descriptors for matching detected points across images.

Uploaded by

asumi288hk
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 26

Local features: main components

1) Detection: Identify the interest


points

2) Description: Extract vector


feature descriptor surrounding x1 = [ x1(1) , ! , xd(1) ]
each interest point.

3) Matching: Determine
correspondence between x 2 = [ x1( 2) ,!, xd( 2) ]
descriptors in two views

Kristen Grauman
Image transformations
• Geometric

Rotation

Scale

• Photometric
Intensity change
Harris detector: Invariance properties
-- Image translation

• Derivatives and window function are shift-invariant


Harris detector: Invariance properties –
Affine intensity change
I®aI+b

• Only derivatives are used =>


invariance to intensity shift I ® I + b
• Intensity scaling: I ® a I

R R
threshold

x (image coordinate) x (image coordinate)

Partially invariant to affine intensity change


Harris Detector: Invariance Properties
• Scaling

Corner

All points will be


classified as edges

Not invariant to scaling


Scale invariant detection
Suppose you’re looking for corners

Key idea: find scale that gives local maximum of f


– in both position and scale
– One definition of f: the Harris operator
Lindeberg
Lindeberg et al,et al., 1996
1996

Slide
Slidefrom
fromTinne
TinneTuytelaars
Tuytelaars
Implementation
• Instead of computing f for larger and larger
windows, we can implement using a fixed
window size with a Gaussian pyramid

(sometimes need to create in-


between levels, e.g. a ¾-size image)
Feature extraction: Corners and blobs
Another common definition of f
• The Laplacian of Gaussian (LoG)

¶ g ¶ g
2 2
Ñ g= 2 + 2
2

¶x ¶y
Laplacian of Gaussian (LoG)
• Consider

Laplacian of Gaussian
operator

Where is the edge? Zero-crossings of bottom graph 18


2D edge detection filters

Laplacian of Gaussian

Gaussian derivative of Gaussian

is the Laplacian operator:

19
Laplacian of Gaussian
• “Blob” detector minima

* =

maximum

• Find maxima and minima of LoG operator in


space and scale
Find local maxima in position-scale space

s5

s4

Lxx (s ) + Lyy (s ) s3

s2

Þ List of
(x, y, s)
s

K. Grauman, B. Leibe
Scale-space blob detector: Example
Scale-space blob detector: Example
Scale-space blob detector: Example
Feature descriptors
We know how to detect good points
Next question: How to match them?

?
Answer: Come up with a descriptor for each point,
find similar descriptors between the two images
Feature descriptors
We know how to detect good points
Next question: How to match them?

?
Lots of possibilities (this was a popular research area)
– Simple option: match square windows around the point
– Popular approach: SIFT
• David Lowe, UBC http://www.cs.ubc.ca/~lowe/keypoints/

You might also like