KEMBAR78
SIFT: Scale-Invariant Keypoint Features | PDF | Computers
Scribd
Upload
696 views16 pages

SIFT: Scale-Invariant Keypoint Features

This document summarizes the Scale-Invariant Feature Transform (SIFT) algorithm proposed by David Lowe. SIFT detects scale-invariant keypoints in images and extracts local feature vectors for image matching and recognition. The algorithm involves detecting stable keypoints at multiple scales, localizing keypoints, and generating feature vectors based on keypoint locations and local image gradients. Keypoints are filtered and refined to achieve scale and rotation invariance. SIFT features are highly distinctive and partially invariant to changes in illumination and 3D viewpoint.

Uploaded by

OpenTechTalk
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
696 views16 pages

SIFT: Scale-Invariant Keypoint Features

This document summarizes the Scale-Invariant Feature Transform (SIFT) algorithm proposed by David Lowe. SIFT detects scale-invariant keypoints in images and extracts local feature vectors for image matching and recognition. The algorithm involves detecting stable keypoints at multiple scales, localizing keypoints, and generating feature vectors based on keypoint locations and local image gradients. Keypoints are filtered and refined to achieve scale and rotation invariance. SIFT features are highly distinctive and partially invariant to changes in illumination and 3D viewpoint.

Uploaded by

OpenTechTalk
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

SIFT - Distinctive Image Features from Scale-Invariant Keypoints

by David G. Lowe

presented by David Strmer

Table of contents
Feature Generation detection of scale-space extrema local extrema detection maxima/minima filtering with thresholds subpixel extrema detection Classification Generation gradient direction/magnitude diagramm on key-point Histogram of directions generate SIFT feature vector

Detection of scale-space extrema

Local extrema detection


search for maxima/minima within a 3x3x3 region performed on results of difference of Gaussian algorithm

Maxima/Minima filtering with thresholds


in local area there a lots of values local extrema can have very small values double thresholding helps to remove "unimportant" points that were created from small difference in source image, such as noise

Subpixel extrema detection


the given data does not represent a signal exactly, because it is sampled position of extrema can be extrapolated by using Tylor expression and setting it to zero the extrema can also get another value this subpixel extrema is done for direction x, y and can also be done for z (between DoG)

Gradient direction/magnitude
Calculate gradient and magnitude of a 16x16 region around key-point create a kind of characteristic of keypoint in location

Histogram of directions
directions are separated into 36 bins with each 10 degrees magnitude of each direction is added on certain bin each bar with a peak over 80% is converted into a separate key-point with its own direction

Generate SIFT feature vector - 1


Aim of this step: generate 128 dimensional feature vector of 16x16 window around key-point

Generate SIFT feature vector - 2


in 4x4 Window gradient an magnitude is calculated foreach, the key-point orientation is subtracted orientation were put in 8 bin histogramm

Generate SIFT feature vector - 2


depending on their distance to key-point, a gaussian weighting function is applied the result: 8 bins with directions this is done for alle 4x4 regions within 16x16 region = 128 directions

Results in my thesis

Results in my thesis

Results in my thesis

Thanks

Sources
http://www.cs.ubc.ca/~lowe/keypoints/ http://en.wikipedia.org/wiki/Scaleinvariant_feature_transform http://www.aishack.in/2010/05/sift-scale-invariant-featuretransform/

You might also like