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

A low-rank locality preserving projection image recognition method based on f-norm

A technology of local preservation of projection and image recognition, used in character and pattern recognition, computer parts, instruments, etc.

Active Publication Date: 2021-07-30
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional LPP method is very sensitive to noise, because the square F norm amplifies the influence of noise on the algorithm

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
  • A low-rank locality preserving projection image recognition method based on f-norm
  • A low-rank locality preserving projection image recognition method based on f-norm
  • A low-rank locality preserving projection image recognition method based on f-norm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Below in conjunction with accompanying drawing and experiment the technical method of this invention is further described.

[0041] Based on the present invention, a kind of image recognition method based on F-norm low-rank local preservation projection is proposed, referring to figure 1 , the specific implementation includes:

[0042] A. Adopt Robust Principal Component Analysis (RPCA) and local preservation projection based on F norm to input original image data X=[x 1 , x 2 ,...,x N ] to build an analysis model where each image x i is a column vector of size

[0043] B. The model is solved by the alternate iteration method to obtain the projection matrix of the image.

[0044] C. Classify unknown images according to the obtained projection matrix.

[0045] Further, the step A is specifically:

[0046] A1. Determine the robust principal component analysis (RPCA) minimum value equation that the input image matrix satisfies, that is, solve the low-rank componen...

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 relates to an image recognition method based on F-norm low-rank local preservation projection, which performs dimensionality reduction on high-dimensional data, and is especially aimed at the situation that there are abnormal values ​​in the image. Specifically, Robust Principal Component Analysis (RPCA) and F-norm-based local preserving projection are used to establish an analysis model for the input original image data; the alternate iteration method is used to solve the model to obtain the projection matrix of the image; according to the obtained projection matrix, the Unknown images are classified. This method uses a low-rank data matrix as input, and uses the F-norm as the distance measurement standard between samples, so that the data with a closer distance in the high-dimensional space will remain close after being projected into the low-dimensional space, thereby maintaining the local structure of the data. .

Description

technical field [0001] The invention is a feature extraction method of machine learning, in particular to an image recognition method based on F-norm low-rank local preservation projection, and is especially suitable for classification with abnormal values ​​in images. Background technique [0002] High-dimensional data is ubiquitous in modern computer vision and image processing research. However, high-dimensional data will not only increase storage overhead and computational complexity, but also reduce the effectiveness of algorithms in practical applications. High-dimensional data are often distributed in low-dimensional subspaces or low-dimensional structures of manifolds. Therefore, finding the mapping relationship between high-dimensional data and low-dimensional space has become an important issue for image classification. Algorithms for data dimensionality reduction have made extensive progress in recent decades. [0003] Locality Preserving Projection (LPP) is a ...

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): G06K9/62
Inventor 孙艳丰尹帅胡永利
Owner BEIJING UNIV OF TECH