Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sparse image classification method based on low-rank supervision

A sparse image and classification method technology, applied in the field of image processing, can solve the problems of not making full use of image sparse representation and low-rank features, poor versatility, etc., and achieve the effect of good discrimination and good classification effect

Inactive Publication Date: 2017-07-18
HARBIN UNIV OF SCI & TECH
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the existing image classification method has poor versatility and does not make full use of the sparse representation and low-rank features of the image, the present invention discloses a sparse image classification method based on low-rank supervision, aiming to provide a generalizable, Good effect, a sparse image classification method based on low-rank supervision that makes full use of image sparse representation and low-rank features

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
  • Sparse image classification method based on low-rank supervision
  • Sparse image classification method based on low-rank supervision
  • Sparse image classification method based on low-rank supervision

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0056] The sparse image classification method based on low-rank supervision in this embodiment, the flow chart is as follows figure 1 shown. This classification method includes the following steps:

[0057] Step a, determining known samples and samples to be classified;

[0058] Step b, calculating the low-rank representation coefficient matrix Z of the sample to be classified;

[0059]Step c, solving the supervisory matrix W according to the low-rank representation coefficient matrix Z;

[0060] Step d, establishing a sparse coding model based on the supervision matrix;

[0061] Step e, iteratively solving the sparse coding model;

[0062] Step f, classifying according to the reconstruction error;

[0063] Step g, calculating and analyzing the classification accuracy rate Rate.

specific Embodiment 2

[0065] The sparse image classification method based on low-rank supervision in this embodiment, on the basis of the specific embodiment 1, further defines the specific method of step a as follows:

[0066] Step a1, input the sample data in the image library, and normalize it;

[0067] Step a2, respectively mark the number of classes of sample data and the number of samples in each class of samples, and divide each class of samples into a known sample matrix X={X 1 , X 2 , X 3 ,...,X k} and the matrix of samples to be classified Y={y 1 ,y 2 ,y 3 ,...,y n},in, Indicates the mth sample vector in the kth class sample, y n Indicates the nth sample vector to be classified; both the sample vector and the sample vector to be classified are vectors obtained by transforming the image matrix in row order.

specific Embodiment 3

[0069] The sparse image classification method based on low-rank supervision in this embodiment, on the basis of the specific embodiment 1, further limits the method of calculating the low-rank representation coefficient matrix Z of the sample to be classified in step b as follows:

[0070] min||Z|| * +λ||E|| 1 s.t.Y=YZ+E (1)

[0071] Among them, E represents the residual matrix, the elements in the matrix Z represent the correlation between samples, λ is the regularization parameter, ||·|| * =∑ i |σ i (Z)|,σ i (·) means to take the i-th singular value of the matrix, s.t.Y=YZ+E means min||Z||*+λ||E|| 1 Restricted by Y=YZ+E, the augmented Lagrangian multiplier method is used to solve the formula (1).

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 belongs to the image processing technology field and especially relates to a sparse image classification method based on low-rank supervision. The method comprises the following steps of determining a known sample and a sample to be classified; calculating a low-rank expression coefficient matrix Z of the sample to be classified; according to the low-rank expression coefficient matrix Z, solving a supervision matrix W; establishing a sparse coding model based on the supervision matrix; carrying out iteration solving on the sparse coding model; according to a reconstruction error, carrying out classification; and calculating and analyzing a classification correct rate Rate. In the invention, through establishing the sparse coding model based on low-rank supervision and providing a solving method of the sparse coding model based on low-rank supervision, simultaneously sparsity of an expression coefficient and an approaching degree of similar samples are restrained; a weight W is expressed and solved by a low rank so that a sample characteristic can be well captured; and then the model possesses a good discriminating ability among samples so that a good classification effect is acquired.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a sparse image classification method based on low-rank supervision. Background technique [0002] With the development of information technology, image information is widely used in various fields to obtain a large amount of content contained in it, which makes people have a lot of demand for image processing technology. As an important part of image processing, image classification has been widely used in artificial intelligence, computer vision, pattern recognition, information search and other technical fields in recent years. Image classification is to classify images according to the information, content, and features in the images, so as to simulate human's visual understanding and logical interpretation of images, so as to achieve the purpose of intelligence. At present, many research departments and commercial companies have begun or are studying ima...

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
IPC IPC(8): G06K9/62
CPCG06F18/2411
Inventor 李骜雷天鸣陈德运林克正孙广路
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com