sift11.zip_sift

An implementation of SIFT detector and descriptor

Andrea Vedaldi

University of California – VisionLab

Contents

1 Introduction 1

2 User reference: the sift function 1

2.1 Scale space parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2

2.2 Detector parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

2.3 Descriptor parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

These notes describe an implementation of the Scale-Invariant Transform Feature (SIFT) interest point detector

and descriptor [1]. This implementation is designed to produce results close to Lowe’s original implementation.

1

The SIFT detector and descriptor are discussed in some depth in the paper [1]. Here we describe the interface to

our implementation and, in the appendix, some technical details.

2 User reference: the sift function

The SIFT detector and the SIFT descriptor are invoked by me ans of the function sift, which provides a unified

interface to both.

Example 1 (Invocation). The following lines run the SIFT detector and descriptor on the image data/test.jpg.

I = imread(’data/test.png’) ;

of the frame, σ for its scale and θ for its orientation. The coordinates (x

the image, which is assigned coordinates (0, 0), and may be fractional numbers (sub-pixel precision). The scale σ is

the smoothing level at which the frame has b ee n detected. This number can also be interpreted as size of the frame,

which is usually visualized as a disk of radius 6σ. Each descriptor is a vector describing coarsely the appearance of

the image patch c orresponding to the frame (further details are discussed in Appendix A.3). Typically this vector

has dimension 128, but this number can be changed by the user as described later.

Once frames and descriptors of two images I

1

and I

2

have been computed, siftmatch can be used to estimate

the pairs of matching features. This function uses Lowe’s method to discard ambiguous matches [1]. The result is

Example 2 (Matching). Let us assume that the images I1 and I2 have been loaded and processed as in the previous

example. The code

matches = siftmatch(descriptors1, descriptors2) ;

stores in matches the matching pairs, one per column.

The package provides some ancillary functions; you can

Example 3 (Visualization). Let I1, I2 and matches be as in the previous example. To visualize the matches issue

Gaussian scale space is the function

= (g

where g

The algorithm make use of another scale space too, called difference of Gaussian (DOG), which is, coarsely speaking,

the scale derivative of the Gaussian scale space.

Since the scale space G(x; σ) represents the same information (the image I(x)) at different levels of scale, it

0

min

where σ

0

The

sift function accepts the following parameters describing the Gaussian scale space being used:

either 0 or −1. Setting o

to −1 has the effect of doubling the image before com puting the Gaussian scale

assumes that the input image is actually (g

according. Us ually σ

is assumed to be half pixel (0.5).