Object recognition from local scale-invariant features
David G. Lowe · IEEE International Conference on Computer Vision (ICCV) · 1999
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.
Cited by 16,227 works. doi:10.1109/iccv.1999.790410
Authors
References
- Color indexing
- Local grayvalue invariants for image retrieval
- Generalizing the Hough transform to detect arbitrary shapes
- Visual learning and recognition of 3-d objects from appearance
- A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry
- Fitting parameterized three-dimensional models to images
- Shape indexing using approximate nearest-neighbour search in high-dimensional spaces
- Three-dimensional object recognition from single two-dimensional images
- A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass Transform
- Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention