Object Recognition from Local Scale-Invariant Features

DMCA

Object Recognition from Local Scale-Invariant Features

Cached

Download Links

Other Repositories/Bibliography

DBLP

by David G. Lowe

Citations:

2661 - 13 self

BibTeX

@MISC{Lowe_objectrecognition,
    author = {David G. Lowe},
    title = {Object Recognition from Local Scale-Invariant Features},
    year = {}
}

OpenURL

Abstract

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest-neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low-residual least-squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially-occluded images with a computation time of under 2 seconds.

Keyphrases

object recognition local scale-invariant feature robust object recognition new class unknown model parameter nearest-neighbor indexing method inferior temporal cortex low-residual least-squares solution image gradient image key local image feature object recognition system final verification illumination change multiple orientation plane stable point image scaling computation time feature share similar property scale space candidate object match primate vision staged filtering approach experimental result local geometric deformation multiple scale cluttered partially-occluded image

DMCA