An improved neighborhood selection method for local projection noise reduction

A local projection noise reduction for nonlinear time series is introduced into fault diagnosis field.

Although widely applied in nonlinear time series analysis,the performance of noise reduction method via local projection is greatly influenced by the selection of neighborhood.

A low frequency rolling bearing fault diagnosis method based on local projective noise reduction;

Experiment indicates that the local projective algorithm can separate background signals and weak fea-ture signals into different orthogona1 sub-spaces.

In this paper an image matching algorithm based on combining subdivision wavelet with local projection entropy is presented, with using the feature of computational cost scanty of second generation wavelet-subdivision wavelet and the dominance of the local projection entropy.

Recognition of character strings based on projection moment invariant;

An object tracking algorithm based on planar projective invariants is proposed,in which the values of invariants for object modeling and tracking are calculated with lines extracted from images.

The cross ratio of volume elements is shown as projective invariant after the spatial projective transformation is properly introduced.

Projective invariants are independent of viewpoints, intrinsic and extrinsic camera parameters and common used in computer vision gradually.