Intro to Sift

Yu Liu 4.17.2012

Why? What? How?

USCT, Dept. EEIS, Yu Liu

3



1. Image Matching in a common and important problem in computer vision. 2. Application in:
◦ ◦ ◦ ◦ ◦ Object or scene recognition 3D reconstruction Stereo correspondence Motion tracking Image Searching



USCT, Dept. EEIS, Yu Liu

4



3. Traditional method: simple corner detectors is not stable when you have images of different scales and rotations.
4. We need a method can solve:
◦ ◦ ◦ ◦ ◦ ◦ Different Scale Rotation Different Illumination Changed Viewpoint Affine Distortion Addition of noise
USCT, Dept. EEIS, Yu Liu 5





SITF is a method for extracting distinctive invariant features, providing robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination.
Raised by David G. Lowe in Distinctive Image Features from Scale-Invariant Keypoints in 2004.
David G. Lowe Computer Science Department 2366 Main Mall University of British Columbia Vancouver, B.C., V6T 1Z4, Canada E-mail: [e-mail]



USCT, Dept. EEIS, Yu Liu

6



Main idea: Extract a set of features, which are invariant to image scaling and rotation, change in illumination and 3D viewpoint.
1. Create Scale space:
◦ Create DoG Pyramid of Images.
Octave 5 Octave 4 Octave 3
…
…



8

…

4

2
…

Octave 2


…

Octave 1

USCT, Dept. EEIS, Yu Liu

7



2. Detect Keypoint:
◦ ◦ ◦ ◦ (1) (2) (3) (4) Scale-space extrema detection Keypoint localization Select optimal keypoints Orientation assignment of Keypoint
D  2 D 1 X  ( 2) X X
 T

Tr  H   r  1  Det  H  r
2

2

USCT, Dept. EEIS, Yu Liu

8



3. Keypoint descriptor: features
◦ ◦ ◦ ◦ Sample region- Around keypoint Rotation by angle of keypoint’s orientation Orientation histogtram entry- descriptor: 4*4*8 Normalization x x y y

3 oct 3 oct 3 oct 3 oct

x

y

USCT, Dept. EEIS, Yu Liu