13 lines
781 B
Text
13 lines
781 B
Text
|
The SIFT algorithm provides the capability to identify key feature points within
|
||
|
|
arbitrary images. It further extracts highly distinct information for each
|
||
|
|
such point and allows to characterize the point invariant to a number of
|
||
|
|
modifications to the image. It is invariant to contrast/brightness changes, to
|
||
|
|
rotation, scaling and partially invariant to other kinds of transformations.
|
||
|
|
The algorithm can be flexibly used to create input data for image matching,
|
||
|
|
object identification and other computer vision related algorithms.
|
||
|
|
|
||
|
|
This package provides an implementation of the SIFT algorithm and a set of
|
||
|
|
utilities to utilize the algorithm to match two or more images. As output, a
|
||
|
|
number of control points are created, which specify one and the same image
|
||
|
|
location in two images.
|