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

Image classification method of extreme learning machine based on tracking differentiator

A technology of tracking differentiators and extreme learning machines, which is applied in the field of image classification of extreme learning machines, can solve the problem of low accuracy of image classification, and achieve the effect of less training time and good training accuracy

Pending Publication Date: 2022-04-08
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the ELM algorithm uses the Moore-Penrose generalized inverse method to solve the output weight matrix, which has certain defects. This method will lead to long calculation time and low image classification accuracy in some cases.

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 classification method of extreme learning machine based on tracking differentiator
  • Image classification method of extreme learning machine based on tracking differentiator
  • Image classification method of extreme learning machine based on tracking differentiator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Examples are given below to describe the present invention in detail.

[0021] The invention provides an image recognition method of an extreme learning machine based on a tracking differentiator, the basic idea of ​​which is: by using the tracking differentiator method to iteratively solve the output weight matrix in the extreme learning machine, thereby completing the modeling, using The training set constructed from the image completes the training of the algorithm model, and the image recognition model obtained by training is used to classify the image.

[0022] The present invention provides a kind of image recognition method based on the extreme learning machine of tracking differentiator, concrete steps are as follows:

[0023] Step 1. Collect the image data set, perform data preprocessing on the image data to obtain the feature vector of the image, and determine the label of the image. The elements in the image data set are recorded as: (x, t), where x is the fe...

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 an image classification method of an extreme learning machine based on a tracking differentiator, and the method comprises the steps: combining a tracking differentiator with an extreme learning machine algorithm, carrying out the iteration updating of an output weight matrix through different operators and the principle of the tracking differentiator when the output weight matrix is solved, and continuously obtaining a better solution of a matrix equation. The characteristics of simple network structure, random parameter generation and the like of a traditional extreme learning machine are reserved, meanwhile, better training precision can be achieved in the aspect of image recognition, the time consumed by model training is shorter, and a new thought and a new approach are provided for improvement and optimization of a machine learning algorithm and image recognition.

Description

technical field [0001] The invention belongs to the technical field of image classification based on machine learning algorithm optimization, and in particular relates to an image classification method of an extreme learning machine based on a tracking differentiator. Background technique [0002] With the continuous development of image recognition technology, machine learning, as a mainstream method to solve artificial intelligence problems, is widely used in image recognition in various fields, and is constantly innovating. Tracking Differentiator (Tracking Differentiator, TD) is a common method in control, which can help researchers obtain the differential information of a certain signal. Extreme Learning Machine (Extreme Learning Machine, ELM) is a feedforward neural network algorithm with a single hidden layer. Due to its simple structure, input weights and deviations can be randomly generated during training, and determined by solving the minimum norm solution of line...

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 Applications(China)
IPC IPC(8): G06V10/764G06K9/62G06V10/774
CPCY02T10/40
Inventor 邹伟东李钰祥夏元清李慧芳张金会翟弟华戴荔刘坤闫莉萍
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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