PukiWiki contents have been moved into SONOTS Plugin (20070703)

Project: Image Matching using Scale Invariant Feature Transform (SIFT)

Table of Contents


Image matching is a fundamental aspect of many problems in computer vision, including object or scene recognition, solving for 3D structure form multiple images, stereo correspondence, and motion tracking. Scale-invariant feature transform (or SIFT) proposed by David Lowe in 2003 is an algorithm for extracting distinctive features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale, rotation, and partially invariant (i.e. robust) to change in 3D viewpoint, addition of noise, and change in illumination. They are well localized in both the spatial and frequency domains, reducing the probability of disruption by occlusion, clutter, or noise. Large numbers of features can be extracted from typical images with efficient algorithms. In addition, the features are highly distinctive, which allows a single feature to be correctly matched with high probability against a large database of features, providing a basis for object and scene recogition.

First Edition: May 2007. Last Modified: May 2007
Tag: Scientific ComputerVision InterestPointDetection ImageMatching Matlab


No left click, sorry. Right click and download the report fileSIFT.pdf

Matlab Codes

My partner wrote half parts of codes for this project. I did not ask him to publish codes here, so codes are not available for everyone now.