Distinctive Image Features from Scale-Invariant Keypoints

DMCA

Distinctive Image Features from Scale-Invariant Keypoints (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by David G. Lowe

Citations:

8952 - 21 self

BibTeX

@MISC{Lowe03distinctiveimage,
    author = {David G. Lowe},
    title = {Distinctive Image Features from Scale-Invariant Keypoints},
    year = {2003}
}

OpenURL

Abstract

This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through leastsquares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

Keyphrases

scale-invariant keypoints distinctive image feature individual feature recognition proceeds leastsquares solution many image identify object hough transform different image distinctive invariant feature image scale object recognition substantial range affine distortion fast nearest-neighbor algorithm single feature high probability consistent pose parameter single object real-time performance large database

DMCA