Proceedings of the International Conference on Computer Vision
Object Recognition from Local Scale-Invariant Features
作者:
Lowe， D.G.
关键词:
computational geometry；feature extraction；image matching；least squares approximations；object recognition；3D projection；blurred image gradients；candidate object matches；cluttered partially occluded images；computation time
摘要:
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.
在线下载