Unlock instant, AI-driven research and patent intelligence for your innovation.

Image data dimensionality reduction method and system based on discriminant regularized locality-preserving projection

A technology that locally preserves projection and image data, applied in the field of image recognition, can solve the problem of insufficient consideration of differences in distribution characteristics, and achieve the effect of avoiding distortion, improving local essential structural characteristics, and maintaining diversity and difference.

Active Publication Date: 2022-04-22
XIAMEN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the scale of the sparse representation has nothing to do, making these methods insufficiently consider the differences in the distribution characteristics of different regions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image data dimensionality reduction method and system based on discriminant regularized locality-preserving projection
  • Image data dimensionality reduction method and system based on discriminant regularized locality-preserving projection
  • Image data dimensionality reduction method and system based on discriminant regularized locality-preserving projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0068] As an implementation manner, step 108 specifically includes:

[0069] Obtain the image to be reduced in dimension;

[0070] Cutting the image to be dimensionally reduced into a sample vector x;

[0071] According to Y=W 'T x performs dimensionality reduction on the image to be reduced in dimensionality, wherein W' is a target projection matrix, and Y is data after dimensionality reduction of the image to be reduced in dimensionality.

[0072] As an implementation manner, the method provided in this embodiment also includes:

[0073] Get the test sample image;

[0074] Cutting the test sample image into test sample vectors;

[0075] performing dimensionality reduction on the test sample vector by using the target projection matrix;

[0076] A classifier is used to identify the test sample vector after dimensionality reduction;

[0077] Evaluate the pros and cons of the projection matrix according to the recognition result.

[0078] In this embodiment, the dimensio...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method and a system for reducing the dimension of image data based on discriminative regularization and partial preservation projection. The method includes: acquiring a sample image; cutting the sample image into sample vectors, performing L2 norm normalization processing on each sample vector, and obtaining a processed sample vector x i ; Determine the first similarity matrix S ij ; according to the determination of the second similarity matrix S' ij , where W is the projection matrix, B ij is an elastic matrix; according to (X(L+λL')X T )V=λ(XDX T )V solves the matrix V and the eigenvalue λ; extracts the eigenvectors corresponding to the relatively large first v eigenvalues ​​in the matrix V to form a projection matrix; jumps to the determination step of determining the second similarity matrix, until the iteration conditions are met, and the final The obtained projection matrix is ​​recorded as the target projection matrix; the target projection matrix is ​​used to reduce the dimension of the image to be reduced. The image data dimensionality reduction method and system provided by the present invention take into account the similarity and difference of data at the same time.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an image data dimensionality reduction method and system based on discriminant regularization local preservation projection. Background technique [0002] Data dimensionality reduction of images is to project high-dimensional data into low-dimensional space while maintaining as much intrinsic information as possible of the original data, so that high-dimensional data can be represented in low-dimensional space. Through this operation, the redundancy of the original data can be reduced, and the efficiency and pertinence of data processing can be improved. The most typical dimensionality reduction methods for linear data dimensionality reduction include: Principal component analysis (PCA) and linear discriminant analysis (Linear discriminant analysis, LDA). These two methods are mature in theory, simple in calculation and fast in calculation speed, but these methods are ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/77G06K9/62
CPCG06F18/213
Inventor 高云龙潘金艳陈福兴
Owner XIAMEN UNIV