libsift 1.8

libsift is an algorithm to identify and locate interesting points within an image. For all such points, a descriptive signature is extracted.
The signatures can be stored and matched among multiple images, allowing for a large number of interesting applications, such as aligning overlapping images and identifying objects or motion within image sequences.
libsift is used by the autopano-sift program to create panorama images.
This library is a 100% C# implementation of the SIFT algorithm ("Scale-Invariant Feature Transform") and additional matching algorithms. The SIFT algorithm is an image feature location and extraction algorithm which provides the following key advantages over similar algorithms:
- Combined feature location and extraction algorithm.
- The keypoint locations are more precise and repeatable, because SIFT uses subpixel localization and multiple scale keypoint identification
- The descriptors are highly distinctive. For example, I tested with up to 300,000 keypoints while matching a large 60 picture panorama and it did not have a single invalid match.
- The feature vectors can be efficiently correlated using probabilistic algorithms like Best-Bin-First kd-tree search.
Enhancements:
- A serious bug in the Gaussian sigma computation and a bug in the DoG scale handling were fixed.